CN103581705A - Method and system for recognizing video program - Google Patents
Method and system for recognizing video program Download PDFInfo
- Publication number
- CN103581705A CN103581705A CN201210440858.0A CN201210440858A CN103581705A CN 103581705 A CN103581705 A CN 103581705A CN 201210440858 A CN201210440858 A CN 201210440858A CN 103581705 A CN103581705 A CN 103581705A
- Authority
- CN
- China
- Prior art keywords
- video
- frame
- digital finger
- information
- 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
Links
Images
Abstract
The invention relates to a method and system for recognizing a video program. The method comprises the steps that S1, video pictures played by a video play terminal are shot; S2, the overall or local feature information of video frames in the video pictures is extracted to generate digital fingerprints describing the video frames; S3, search matching is carried out on a video frame fingerprint database through the generated digital fingerprints, and program information corresponding to the video frames is acquired through a matching result. The video frame digital fingerprints are generated through the shot video pictures of the video play terminal, the search matching is carried out in the video frame fingerprint database to obtain the corresponding program information, and therefore recognition speed is high, the precision degree is high, and real-time requirements are met. Related information resources on a network are searched for and obtained through the recognized program information and are returned to a mobile communication terminal, a user can acquire the related information of a television program being watched by the user conveniently and fast when watching the video program, the operation is simple, real-time performance is strong, and the user experience effect is good.
Description
Technical field
The present invention relates to Video processing, more particularly, relate to a kind of video frequency program recognition methods and system.
Background technology
Along with the raising of people's living standard, demand is also in continuous increase.User, when watching TV programme, has not been only the programme information that unidirectional reception is televised as before, and has expected to have more understanding and interaction.Although the appearance of Web TV can meet user's some demands in this respect, but, in prior art, if user is interested in and want to understand the relevant information of this program the TV programme of current broadcasting, television set need to be switched to net state from program broadcast state, or surf the Net with PC.The operation complexity of this method is high, and for the user that can not surf the Net, difficulty is very large, and this method does not have real-time and interactive, and user's experience effect is very poor.
Summary of the invention
The technical problem to be solved in the present invention is, for the above-mentioned defect of prior art, provides a kind of video frequency program recognition methods and system that can facilitate user to get quickly and easily video frequency program relevant information.
The technical solution adopted for the present invention to solve the technical problems is: propose a kind of video frequency program recognition methods, comprise the steps:
The video pictures that S1, capture video playback terminal are play;
S2, the overall situation of extracting frame of video in this video pictures and local characteristic information are to generate the digital finger-print of describing this frame of video;
S3, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.
In above-mentioned video frequency program recognition methods, described step S2 further comprises:
Video playing terminal frame in the video pictures that S21, detection photograph, the content of extraction frame of video;
S22, the content of frame of video is carried out to signature analysis to extract the overall situation and the local characteristic information of frame of video;
S23, the overall situation based on frame of video and local characteristic information generate the digital finger-print of describing this frame of video.
In above-mentioned video frequency program recognition methods, described video pictures comprises live video picture and order video picture, and when described video pictures is live video picture, described step S3 further comprises:
S31, obtain in advance the program inventory of television channel;
S32, with the digital finger-print search frame of video fingerprint database generating to find matching result, get the channel information relevant to this digital finger-print;
S33, according to the temporal information of this channel information and digital finger-print, search program inventory, obtain programme information corresponding to this frame of video.
The present invention also proposes a kind of video frequency program recognition system for solving its technical problem, comprising:
Frame of video fingerprint database, for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information;
Communication terminal, the video pictures of playing for capture video playback terminal, extracts the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describes the digital finger-print of this frame of video;
Digital finger-print search match server, the digital finger-print sending for receiving communication terminal, and with this digital finger-print, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.
Above-mentioned video frequency program recognition system also comprises:
Frame of video fingerprint generation server, for generating the frame of video digital finger-print of order video program and deposit it in frame of video fingerprint database with the index of corresponding programme information in advance, and generate in real time the frame of video digital finger-print of live video program and deposit it in frame of video fingerprint database with the index of corresponding programme information.
In above-mentioned video frequency program recognition system, described communication terminal further comprises:
Taking module, the video pictures of playing for capture video playback terminal;
Frame detection module, for detection of the video playing terminal frame in the video pictures photographing, extracts the content of frame of video;
Characteristic extracting module, for carrying out signature analysis to extract the overall situation and the local characteristic information of frame of video to the content of frame of video;
Digital finger-print generation module, generates for the overall situation based on frame of video and local characteristic information the digital finger-print of describing this frame of video;
Sending module, for sending to the digital finger-print of generation digital finger-print search match server.
In above-mentioned video frequency program recognition system, described digital finger-print search match server further comprises:
Memory module, for storing the program inventory of the television channel obtaining in advance;
Digital finger-print receiver module, the digital finger-print sending for receiving communication terminal;
Fingerprint search module, the digital finger-print receiving with digital finger-print receiver module search frame of video fingerprint database is to find the digital finger-print of coupling;
Order video programme information locating module, searches corresponding programme information based on matching result while being order video frame of digital fingerprint for the digital finger-print in described coupling;
Live video channel locating module, searches corresponding channel information based on matching result while being live video frame of digital fingerprint for the digital finger-print in described coupling;
Live video programme information locating module, for searching program inventory according to the temporal information of this channel information and digital finger-print, obtains programme information corresponding to this frame of video.
In above-mentioned video frequency program recognition system, described frame of video fingerprint generation server further comprises:
Video decode module, for decoding video images with generating video frame;
Duplicate removal module, for detection of and remove similar frame of video;
Characteristic extracting module, for carrying out signature analysis to extract the overall situation and the local characteristic information of frame of video to the content of frame of video;
Digital finger-print generation module, generates for the overall situation based on frame of video and local characteristic information the digital finger-print of describing this frame of video;
Sending module, for sending to frame of video fingerprint database by the digital finger-print of generation.
The present invention also proposes a kind of video frequency program recognition methods for solving its technical problem, comprises the steps:
The video pictures that S1, capture video playback terminal are play;
S2, the overall situation of extracting frame of video in this video pictures and local characteristic information are to generate the digital finger-print of describing this frame of video;
S3, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video;
S4, search for and obtain the information resources that are associated with this programme information on network.
The present invention also proposes a kind of video frequency program recognition system for solving its technical problem, comprising:
Frame of video fingerprint database, for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information;
Communication terminal, the video pictures of playing for capture video playback terminal, extracts the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describes the digital finger-print of this frame of video;
Digital finger-print search match server, the digital finger-print sending for receiving communication terminal, and with this digital finger-print, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video;
Video Web information server, for the information resources on the program information search network sending based on digital finger-print search match server, and sends to described communication terminal by the network information resource being associated with this programme information.
Video frequency program recognition methods of the present invention and system are utilized the video pictures in the video playing terminal such as camera televising machine of the communication terminals such as mobile phone, use the overall situation and the local characteristic information of frame of video to generate the digital finger-print of describing this frame of video, utilize this digital finger-print to search for coupling to frame of video fingerprint database, by matching result, get corresponding programme information, thereby recognition speed is fast, identification precision is high, and can meet requirement of real time.Further, technical scheme of the present invention can be utilized the program information search identifying and obtain the communication terminal that relevant information resource on network returns to user, thereby, user can the mode by mobile phone photograph just can be known quickly and easily the relevant information of the TV programme of watching when watching video frequency program, simple to operate, real-time, user's experience effect is good.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described, in accompanying drawing:
Fig. 1 is the flow chart of the video frequency program recognition methods of one embodiment of the invention;
Fig. 2 is the flow chart of the specific embodiment of step 130 in Fig. 1;
Fig. 3 is the flow chart of the specific embodiment of step 140 in Fig. 1;
Fig. 4 is the building-block of logic of the video frequency program recognition system of one embodiment of the invention;
Fig. 5 is the building-block of logic of communication terminal in one embodiment of the invention;
Fig. 6 is the building-block of logic of frame of video fingerprint generation server in one embodiment of the invention;
Fig. 7 is the building-block of logic of digital finger-print search match server in one embodiment of the invention;
Fig. 8 is the flow chart of the video frequency program recognition methods of another embodiment of the present invention;
Fig. 9 is the building-block of logic of the video frequency program recognition system of another embodiment of the present invention;
Figure 10 is an application scenarios schematic diagram of video frequency program recognition methods of the present invention.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Fig. 1 shows the flow chart of the video frequency program recognition methods of one embodiment of the invention.As shown in Figure 1, this video frequency program recognition methods 100 starts from step 110.
Subsequently, at next step 120, the video pictures that capture video playback terminal is play.
Subsequently, at next step 130, extract the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describe the digital finger-print of this frame of video.The specific implementation that features relevant is extracted and digital finger-print generates, will be in the follow-up detailed description that provides.
Subsequently, at next step 140, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.In specific embodiment, the video frequency program that video playing terminal is play can be live video program (for example live television programming), can be also order video program.For order video program, pre-stored frame of video digital finger-print and the corresponding programme information that has this video frequency program of frame of video fingerprint database, therefore,, as long as find the digital finger-print of coupling in frame of video fingerprint database, just can obtain the programme information of the frame of video of shooting.For live video program, the frame of video digital finger-print that frame of video finger print data library storage generates in real time for this live video program and corresponding programme information, in conjunction with the television channel program inventory obtaining in advance, just can find programme information corresponding to frame of video.Relevant live video frame of digital fingerprint search is criticized the specific implementation of coupling, will be in the follow-up detailed description that provides.
Finally, method 100 ends at step 150.
Fig. 2 is the flow chart of the specific embodiment of step 130 in Fig. 1.As shown in Figure 2, the idiographic flow of step 130 starts from step 131.
Subsequently, at next step 132, detect the video playing terminal frame in the video pictures photographing, extract the content of frame of video.For example, in televising machine sowing, put video pictures time, unavoidably television set and even television set environmental background of living in all can be taken into, therefore, when carrying out video frequency program identification, first to from the picture of taking, detect TV frame, to the program picture video frame of TV actual play is extracted from picture background.In specific embodiment, the detection of frame and the extraction of frame of video, can realize by existing various applicable algorithms.
Subsequently, at next step 133, the content of frame of video is carried out to signature analysis to extract the overall situation and the local characteristic information of frame of video.More existing video identification technologies some partial picture information such as word based on extracting on TV station symbol or tv programme picture are identified video frequency program, and this technology has larger application limitation, and television image is had to more intense restrictive condition.For example, on network, a lot of videos all do not have TV station symbol at present, there is no the information such as word yet, and prior art cannot realize identification; Programme televised live has the situation of relay, and there will be misleading based on TV station symbol recognition video frequency program this time; Under current same province platform, a plurality of channels can be used same station symbol, and TV station symbol recognition cannot be distinguished province's program map.The present invention combines use by the overall situation of frame of video and local characteristic information, and than identifying video frequency program based on local message, much smaller to the restrictive condition of tv programme picture, identification accuracy is improved.
Subsequently, at next step 134, the overall situation based on frame of video and local characteristic information generate the digital finger-print of describing this frame of video.In preferred embodiment, can carry out the digital finger-print that vision hash algorithm processes to generate this frame of video of description to the overall situation of frame of video and local characteristic information.This digital finger-print can be a binary string, and size is in 1K size of data.
Finally, the idiographic flow of step 130 ends at step 135.
As previously mentioned, video pictures comprises live video picture and order video picture.Fig. 3 shows the flow chart of the specific embodiment of step 140 when identification live video picture in Fig. 1.As shown in Figure 3, the idiographic flow of step 140 when identification live video picture starts from step 141.
Subsequently, at next step 142, obtain in advance the program inventory of television channel.
Subsequently, at next step 143, with the digital finger-print search frame of video fingerprint database generating, to find matching result, get the channel information relevant to this digital finger-print, navigate to the current channel of watching of user.
Subsequently, at next step 144, according to the temporal information of this channel information and digital finger-print, search program inventory, just can obtain programme information corresponding to this frame of video.
Finally, the idiographic flow of step 140 ends at step 145.
Fig. 4 shows the building-block of logic of the video frequency program recognition system of one embodiment of the invention.As shown in Figure 4, this video frequency program recognition system 200 comprises communication terminal 220, digital finger-print search match server 230, frame of video fingerprint database 240 and frame of video fingerprint generation server 250.Wherein, the video pictures that communication terminal 220 is play for capture video playback terminal 210, and extract the overall situation of frame of video in this video pictures and local characteristic information to generate the digital finger-print of describing this frame of video, then the digital finger-print of generation is sent to digital finger-print search match server 230 to search corresponding programme information.Specifically, communication terminal 220 can be such as mobile phone, panel computer etc. with camera and there is user's handheld terminal of network savvy, video playing terminal 210 can be the video playback apparatus such as general television set, intelligent TV set, computer.The digital finger-print that digital finger-print search match server 230 sends for receiving communication terminal 220, and with this digital finger-print, frame of video fingerprint database 240 is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.Further, digital finger-print search match server 230 can also send it back communication terminal 220 by the programme information getting.Frame of video fingerprint generation server 250 is for generating in advance the frame of video digital finger-print of order video program and depositing it in frame of video fingerprint database 240 with the index of corresponding programme information, and generates in real time the frame of video digital finger-print of live video program and deposit it in frame of video fingerprint database 240 with the index of corresponding programme information.In specific embodiment, frame of video fingerprint generation server 250 can comprise again live video frame fingerprint generation server and order video frame fingerprint generation server, provides live video frame of digital fingerprint and order video frame of digital fingerprint respectively to frame of video fingerprint database 240.Frame of video fingerprint database 240 for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information.In specific embodiment, frame of video fingerprint database 240 can comprise again live video frame fingerprint database and order video frame fingerprint database, stores respectively live video frame of digital fingerprint and order video frame of digital fingerprint.
In a specific embodiment, as shown in Figure 5, communication terminal 220 further comprises taking module 221, frame detection module 222, characteristic extracting module 223, digital finger-print generation module 224 and sending module 225.The video pictures that taking module 221 capture video playback terminals 210 are play.Frame detection module 222 detects the video playing terminal frame in the video pictures that taking modules 221 photograph, and extracts the content of frame of video, then sends to characteristic extracting module 223.The content of 223 pairs of frame of video of characteristic extracting module is carried out signature analysis to extract the overall situation and the local characteristic information of frame of video.The overall situation of the frame of video that digital finger-print generation module 224 extracts based on characteristic extracting module 223 and local characteristic information generate the digital finger-print of describing this frame of video.In preferred embodiment, the overall situation of the frame of video that digital finger-print generation module 224 can extract characteristic extracting module 223 and local characteristic information carry out vision hash algorithm and process to generate the digital finger-print of describing this frame of video, this digital finger-print can be size at 1K with interior binary string.Then, the digital finger-print that sending module 225 generates digital finger-print generation module 224 sends to digital finger-print search match server 230 to search for coupling.
Further as shown in Figure 7, digital finger-print search match server 230 comprises digital finger-print receiver module 231, fingerprint search module 232, order video programme information locating module 233, live video channel locating module 234, live video programme information locating module 235 and memory module 236.In memory module 236, store the program inventory of the television channel obtaining in advance.Digital finger-print receiver module 231 receives the digital finger-print that communication terminal 220 sends, and the digital finger-print search frame of video fingerprint database 240 that then fingerprint search module 232 use digital finger-print receiver modules 231 receive is to find the digital finger-print of coupling.Specifically, digital finger-print search match server 230 is slightly different for the processing of order video program and live video program.For order video program, the matching result that order video programme information locating module 233 finds based on fingerprint search module 232 is searched corresponding programme information.For live video program, the matching result that live video channel locating module 234 finds based on fingerprint search module 232 is searched corresponding channel information, then, the program inventory that live video programme information locating module 235 is searched television channel pre-stored in memory module 236 according to the temporal information of this channel information and digital finger-print, obtains programme information corresponding to this frame of video.
Again as shown in Figure 6, frame of video fingerprint generation server 250 further comprises video decode module 251, duplicate removal module 252, characteristic extracting module 253, digital finger-print generation module 254 and sending module 255.The video image of the live or order video program of video decode module 251 decoding is with generating video frame.Duplicate removal module 252 detects and removes similar frame of video in the frame of video that video decode module 251 generates.In video frequency program, the quantity of frame of video is very huge, the picture that has 25 frame left and right for general one second, but in video flowing, there is much continuous, closely similar frame picture, thereby detect and remove similar frame picture, can greatly reduce the size of frame of video fingerprint database, and accelerate fingerprint formation speed.The content of the frame of video after 253 pairs of duplicate removals of characteristic extracting module is carried out signature analysis to extract the overall situation and the local characteristic information of frame of video, offer digital finger-print generation module 254, the overall situation by digital finger-print generation module 254 based on frame of video and local characteristic information generate the digital finger-print of describing this frame of video.In preferred embodiment, the overall situation of 254 pairs of frame of video of digital finger-print generation module and local characteristic information carry out vision hash algorithm and process to generate the digital finger-print of describing this frame of video.Sending module 255 sends to frame of video fingerprint database 240 for the digital finger-print that digital finger-print generation module 254 is generated.
Fig. 8 shows the flow chart of the video frequency program recognition methods 300 of another embodiment of the present invention.This video frequency program recognition methods 300 is a kind of expanded application of the video frequency program recognition methods 100 shown in Fig. 1.As shown in Figure 8, this video frequency program recognition methods 300 starts from step 310.
Subsequently, at next step 320, the video pictures that capture video playback terminal is play.
Subsequently, at next step 330, extract the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describe the digital finger-print of this frame of video.
Subsequently, at next step 340, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.
Subsequently, at next step 350, search for and obtain the information resources that are associated with this programme information on network, such as the picture relevant to this programme information, news, website, video, microblogging etc.
Finally, method 300 ends at step 360.
By said method, user can get easily in real time information resources relevant to watched program on network when watching video frequency program, improves interactive while watching program.
Fig. 9 shows the building-block of logic of the video frequency program recognition system 400 of another embodiment of the present invention.This video frequency program recognition system 400 is a kind of expanded application of the video frequency program recognition system 200 shown in Fig. 4.As shown in Figure 9, this video frequency program recognition system 400 comprises communication terminal 420, digital finger-print search match server 430, frame of video fingerprint database 440, frame of video fingerprint generation server 450 and video Web information server 460.Wherein, the video pictures that communication terminal 420 is play for capture video playback terminal 410, and extract the overall situation of frame of video in this video pictures and local characteristic information to generate the digital finger-print of describing this frame of video, then the digital finger-print of generation is sent to digital finger-print search match server 430 to search corresponding programme information.Digital finger-print search match server 430 receives the digital finger-print that communication terminal 420 sends, and with this digital finger-print, frame of video fingerprint database 440 is searched for to coupling, by matching result, gets the programme information corresponding with this frame of video.Frame of video fingerprint generation server 450 is for generating in advance the frame of video digital finger-print of order video program and depositing it in frame of video fingerprint database 440 with the index of corresponding programme information, and generates in real time the frame of video digital finger-print of live video program and deposit it in frame of video fingerprint database 440 with the index of corresponding programme information.Frame of video fingerprint database 440 for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information.The specific implementation of the search of the communication terminal 420 of system 400, digital finger-print match server 430, frame of video fingerprint database 440 and frame of video fingerprint generation server 450, can be referring to above in conjunction with the description of Fig. 4-7 pair system 200.
Video Web information server 460 receives from digital finger-print search match server 430 programme information recognizing, information resources based on this program information search network (such as the picture relevant to this programme information, news, website, video, microblogging etc.), and the network information resource being associated with this programme information is sent it back to communication terminal 420.So just, can realize user and when watching video frequency program, get easily in real time information resources relevant to watched program on network.
Video frequency program recognition methods of the present invention and system are utilized the video pictures in the video playing terminal such as camera televising machine of the communication terminals such as mobile phone, use the overall situation and the local characteristic information of frame of video to generate the digital finger-print of describing this frame of video, utilize this digital finger-print to search for coupling to frame of video fingerprint database, by matching result, get corresponding programme information, and can utilize the program information search identifying and obtain the communication terminal that relevant information resource on network returns to user, thereby, user can the mode by mobile phone photograph just can be known quickly and easily the relevant information of the TV programme of watching when watching video frequency program, simple to operate, real-time, user's experience effect is good.Figure 10 just shows an application scenarios of video frequency program recognition methods of the present invention.As shown in figure 10, user is when watching the TV programme of television for play, may need to understand some information relevant to this TV programme, for example performer's relevant information in the background information of program, program, other people are to comment of this program etc., if at this moment look into these data with online computing, be very inconvenient, and for some old spectators, can not use online computing, just be difficult to obtain these information.Mobile phone is that user carries conveniently, based on the present invention, user can utilize the application APP in mobile phone by the camera of mobile phone, the television image of television for play to be taken pictures, then by this application APP, extract the digital finger-print of frame of video in television image, by communication network, be uploaded to the digital finger-print search match server on backstage.After the digital finger-print that digital finger-print search match server is uploaded at the mobile phone of receiving user, this digital finger-print is mated with the digital finger-print in frame of video fingerprint database, by matching result, get the programme information corresponding with the program of playing on television set.Then, digital finger-print search match server can send to the searching request that carries this programme information video web information server, by video web information server, search for and obtain the information resources that are associated with this programme information on network, such as the picture relevant to this programme information, news, website, video, microblogging etc., and network of relation information resources are returned to user's mobile phone by communication network, by the application APP on mobile phone, present to user.
Shown in Figure 10, be only a kind of example of application scenarios of the present invention, be not limited to the present invention.In different embodiment, the present invention also can be used for various occasions, for example, and the identification of the video frequency program of playing for video playing terminal in building, subway, public transport, this video frequency program is also not limited only to live television programming, also comprises various order videos, various advertisement videos etc.
By method step, described technical characterictic of the present invention and relation thereof above, the compass of described method step and order are to define arbitrarily for convenience of description.As long as can realize this technical characterictic and relation thereof, also can apply other boundary and order.Therefore any other such boundary or order fall into scope and spirit essence of the present invention.
Below also by functional module, technical characterictic of the present invention and relation thereof are described.The boundary of described functional module and the relation of each functional module are to define arbitrarily for convenience of description.As long as can realize this technical characterictic and relation thereof, also can apply other boundary or relation.Therefore any other such boundary or relation also fall into scope and spirit essence of the present invention.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any modifications of doing within the spirit and principles in the present invention, be equal to and replace and improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. a video frequency program recognition methods, is characterized in that, comprises the steps:
The video pictures that S1, capture video playback terminal are play;
S2, the overall situation of extracting frame of video in this video pictures and local characteristic information are to generate the digital finger-print of describing this frame of video;
S3, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.
2. method according to claim 1, is characterized in that, described step S2 further comprises:
Video playing terminal frame in the video pictures that S21, detection photograph, the content of extraction frame of video;
S22, the content of frame of video is carried out to signature analysis to extract the overall situation and the local characteristic information of frame of video;
S23, the overall situation based on frame of video and local characteristic information generate the digital finger-print of describing this frame of video.
3. method according to claim 1, is characterized in that, described video pictures comprises live video picture and order video picture, and when described video pictures is live video picture, described step S3 further comprises:
S31, obtain in advance the program inventory of television channel;
S32, with the digital finger-print search frame of video fingerprint database generating to find matching result, get the channel information relevant to this digital finger-print;
S33, according to the temporal information of this channel information and digital finger-print, search program inventory, obtain programme information corresponding to this frame of video.
4. a video frequency program recognition system, is characterized in that, comprising:
Frame of video fingerprint database, for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information;
Communication terminal, the video pictures of playing for capture video playback terminal, extracts the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describes the digital finger-print of this frame of video;
Digital finger-print search match server, the digital finger-print sending for receiving communication terminal, and with this digital finger-print, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video.
5. system according to claim 4, is characterized in that, described system also comprises:
Frame of video fingerprint generation server, for generating the frame of video digital finger-print of order video program and deposit it in frame of video fingerprint database with the index of corresponding programme information in advance, and generate in real time the frame of video digital finger-print of live video program and deposit it in frame of video fingerprint database with the index of corresponding programme information.
6. system according to claim 5, is characterized in that, described communication terminal further comprises:
Taking module, the video pictures of playing for capture video playback terminal;
Frame detection module, for detection of the video playing terminal frame in the video pictures photographing, extracts the content of frame of video;
Characteristic extracting module, for carrying out signature analysis to extract the overall situation and the local characteristic information of frame of video to the content of frame of video;
Digital finger-print generation module, generates for the overall situation based on frame of video and local characteristic information the digital finger-print of describing this frame of video;
Sending module, for sending to the digital finger-print of generation digital finger-print search match server.
7. system according to claim 5, is characterized in that, described digital finger-print search match server further comprises:
Memory module, for storing the program inventory of the television channel obtaining in advance;
Digital finger-print receiver module, the digital finger-print sending for receiving communication terminal;
Fingerprint search module, the digital finger-print receiving with digital finger-print receiver module search frame of video fingerprint database is to find the digital finger-print of coupling;
Order video programme information locating module, searches corresponding programme information based on matching result while being order video frame of digital fingerprint for the digital finger-print in described coupling;
Live video channel locating module, searches corresponding channel information based on matching result while being live video frame of digital fingerprint for the digital finger-print in described coupling;
Live video programme information locating module, for searching program inventory according to the temporal information of this channel information and digital finger-print, obtains programme information corresponding to this frame of video.
8. system according to claim 5, is characterized in that, described frame of video fingerprint generation server further comprises:
Video decode module, for decoding video images with generating video frame;
Duplicate removal module, for detection of and remove similar frame of video;
Characteristic extracting module, for carrying out signature analysis to extract the overall situation and the local characteristic information of frame of video to the content of frame of video;
Digital finger-print generation module, generates for the overall situation based on frame of video and local characteristic information the digital finger-print of describing this frame of video;
Sending module, for sending to frame of video fingerprint database by the digital finger-print of generation.
9. a video frequency program recognition methods, is characterized in that, comprises the steps:
The video pictures that S1, capture video playback terminal are play;
S2, the overall situation of extracting frame of video in this video pictures and local characteristic information are to generate the digital finger-print of describing this frame of video;
S3, with the digital finger-print generating, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video;
S4, search for and obtain the information resources that are associated with this programme information on network.
10. a video frequency program recognition system, is characterized in that, comprising:
Frame of video fingerprint database, for store real-time existence and the video frequency program frame of video digital finger-print generating in advance and with the index of corresponding programme information;
Communication terminal, the video pictures of playing for capture video playback terminal, extracts the overall situation and the local characteristic information of frame of video in this video pictures and with generation, describes the digital finger-print of this frame of video;
Digital finger-print search match server, the digital finger-print sending for receiving communication terminal, and with this digital finger-print, frame of video fingerprint database is searched for to coupling, by matching result, get the programme information corresponding with this frame of video;
Video Web information server, for the information resources on the program information search network sending based on digital finger-print search match server, and sends to described communication terminal by the network information resource being associated with this programme information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210440858.0A CN103581705A (en) | 2012-11-07 | 2012-11-07 | Method and system for recognizing video program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210440858.0A CN103581705A (en) | 2012-11-07 | 2012-11-07 | Method and system for recognizing video program |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103581705A true CN103581705A (en) | 2014-02-12 |
Family
ID=50052476
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210440858.0A Pending CN103581705A (en) | 2012-11-07 | 2012-11-07 | Method and system for recognizing video program |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103581705A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945234A (en) * | 2014-03-27 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Video-related information providing method and device |
CN103942275A (en) * | 2014-03-27 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Video identification method and device |
CN104038775A (en) * | 2014-06-05 | 2014-09-10 | Tcl集团股份有限公司 | Method and device for identifying channel information |
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 |
CN104185032A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video identification method and system |
CN104506946A (en) * | 2014-12-04 | 2015-04-08 | 南京阅视网络科技有限公司 | Television program identification method based on image identification and system thereof |
CN104540003A (en) * | 2015-01-23 | 2015-04-22 | 广州视源电子科技股份有限公司 | Television programme retrieval method and television programme retrieval device |
CN104994426A (en) * | 2014-07-07 | 2015-10-21 | Tcl集团股份有限公司 | Method and system of program video recognition |
WO2015188629A1 (en) * | 2014-06-13 | 2015-12-17 | Tencent Technology (Shenzhen) Company Limited | Method and system for client-server real-time interaction based on streaming media |
CN105307047A (en) * | 2015-10-15 | 2016-02-03 | 三星电子(中国)研发中心 | Television terminal based service operating method and system |
CN105430469A (en) * | 2015-11-24 | 2016-03-23 | 小米科技有限责任公司 | Method and device for playing audio/video data, terminal and server |
CN105893423A (en) * | 2015-12-03 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | Video recommendation method and system, terminal and server |
CN106233746A (en) * | 2014-08-21 | 2016-12-14 | 松下知识产权经营株式会社 | Content identification device and content identification method |
CN106412690A (en) * | 2015-07-23 | 2017-02-15 | 无锡天脉聚源传媒科技有限公司 | Determination method and device of video playing |
CN106601243A (en) * | 2015-10-20 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Video file identification method and device |
WO2017096801A1 (en) * | 2015-12-09 | 2017-06-15 | 乐视控股(北京)有限公司 | Information processing method and device |
WO2018000642A1 (en) * | 2016-06-29 | 2018-01-04 | 乐视控股(北京)有限公司 | Method, terminal and server for identifying program channel |
CN108271073A (en) * | 2016-12-28 | 2018-07-10 | 上海昕丝文化传播有限公司 | SDK flow chart of data processing |
CN108566562A (en) * | 2018-05-02 | 2018-09-21 | 中广热点云科技有限公司 | Copyright video information structuring arranges the method for completing sample approved sample |
CN108702524A (en) * | 2016-02-29 | 2018-10-23 | 格雷斯诺特公司 | It is identified using more matching detections and the media channel of location-based disambiguation |
CN110113677A (en) * | 2018-02-01 | 2019-08-09 | 阿里巴巴集团控股有限公司 | The generation method and device of video subject |
US10440430B2 (en) | 2016-02-29 | 2019-10-08 | Gracenote, Inc. | Media channel identification with video multi-match detection and disambiguation based on audio fingerprint |
US10567835B2 (en) | 2016-02-29 | 2020-02-18 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
CN111193946A (en) * | 2018-11-15 | 2020-05-22 | 北京盛世辉科技有限公司 | Network interaction control terminal, network interaction system and network interaction communication method |
CN111614991A (en) * | 2020-05-09 | 2020-09-01 | 咪咕文化科技有限公司 | Video progress determination method and device, electronic equipment and storage medium |
CN112203139A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Program content identification method and intelligent system of intelligent television |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090324199A1 (en) * | 2006-06-20 | 2009-12-31 | Koninklijke Philips Electronics N.V. | Generating fingerprints of video signals |
CN102185878A (en) * | 2011-02-18 | 2011-09-14 | 华为技术有限公司 | Method and system for obtaining television program information |
CN102208026A (en) * | 2011-05-27 | 2011-10-05 | 电子科技大学 | Method for extracting digital video fingerprints |
CN102223581A (en) * | 2011-06-28 | 2011-10-19 | 宇龙计算机通信科技(深圳)有限公司 | Video program searching method and video playing terminal |
CN102411578A (en) * | 2010-09-25 | 2012-04-11 | 盛乐信息技术(上海)有限公司 | Multimedia playing system and method |
CN202998337U (en) * | 2012-11-07 | 2013-06-12 | 深圳新感易搜网络科技有限公司 | Video program identification system |
-
2012
- 2012-11-07 CN CN201210440858.0A patent/CN103581705A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090324199A1 (en) * | 2006-06-20 | 2009-12-31 | Koninklijke Philips Electronics N.V. | Generating fingerprints of video signals |
CN102411578A (en) * | 2010-09-25 | 2012-04-11 | 盛乐信息技术(上海)有限公司 | Multimedia playing system and method |
CN102185878A (en) * | 2011-02-18 | 2011-09-14 | 华为技术有限公司 | Method and system for obtaining television program information |
CN102208026A (en) * | 2011-05-27 | 2011-10-05 | 电子科技大学 | Method for extracting digital video fingerprints |
CN102223581A (en) * | 2011-06-28 | 2011-10-19 | 宇龙计算机通信科技(深圳)有限公司 | Video program searching method and video playing terminal |
CN202998337U (en) * | 2012-11-07 | 2013-06-12 | 深圳新感易搜网络科技有限公司 | Video program identification system |
Cited By (69)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104185032B (en) * | 2014-02-26 | 2018-05-11 | 无锡天脉聚源传媒科技有限公司 | A kind of video frequency identifying method and system |
CN104185032A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video identification method and system |
CN103945234A (en) * | 2014-03-27 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Video-related information providing method and device |
CN103942275A (en) * | 2014-03-27 | 2014-07-23 | 百度在线网络技术(北京)有限公司 | Video identification method and device |
CN103942275B (en) * | 2014-03-27 | 2019-03-19 | 百度在线网络技术(北京)有限公司 | A kind of video frequency identifying method and equipment |
CN104038775A (en) * | 2014-06-05 | 2014-09-10 | Tcl集团股份有限公司 | Method and device for identifying channel information |
CN104038775B (en) * | 2014-06-05 | 2018-02-16 | Tcl集团股份有限公司 | A kind of channel information recognition methods and device |
WO2015188629A1 (en) * | 2014-06-13 | 2015-12-17 | Tencent Technology (Shenzhen) Company Limited | Method and system for client-server real-time interaction based on streaming media |
CN104994426A (en) * | 2014-07-07 | 2015-10-21 | Tcl集团股份有限公司 | Method and system of program video recognition |
CN104994426B (en) * | 2014-07-07 | 2020-07-21 | Tcl科技集团股份有限公司 | Program video identification method and system |
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 |
CN104166685B (en) * | 2014-07-24 | 2017-07-11 | 北京捷成世纪科技股份有限公司 | A kind of method and apparatus for detecting video segment |
CN106233746A (en) * | 2014-08-21 | 2016-12-14 | 松下知识产权经营株式会社 | Content identification device and content identification method |
CN104506946A (en) * | 2014-12-04 | 2015-04-08 | 南京阅视网络科技有限公司 | Television program identification method based on image identification and system thereof |
CN104506946B (en) * | 2014-12-04 | 2017-12-05 | 南京阅视网络科技有限公司 | A kind of TV programme recognition methods and system based on image recognition |
CN104540003A (en) * | 2015-01-23 | 2015-04-22 | 广州视源电子科技股份有限公司 | Television programme retrieval method and television programme retrieval device |
CN104540003B (en) * | 2015-01-23 | 2018-05-01 | 广州视源电子科技股份有限公司 | TV program search method and device |
CN106412690A (en) * | 2015-07-23 | 2017-02-15 | 无锡天脉聚源传媒科技有限公司 | Determination method and device of video playing |
CN106412690B (en) * | 2015-07-23 | 2020-01-10 | 无锡天脉聚源传媒科技有限公司 | Video playing determination method and device |
CN105307047B (en) * | 2015-10-15 | 2018-11-20 | 三星电子(中国)研发中心 | A kind of method for operating traffic thereof and system based on television terminal |
CN105307047A (en) * | 2015-10-15 | 2016-02-03 | 三星电子(中国)研发中心 | Television terminal based service operating method and system |
CN106601243A (en) * | 2015-10-20 | 2017-04-26 | 阿里巴巴集团控股有限公司 | Video file identification method and device |
CN106601243B (en) * | 2015-10-20 | 2020-11-06 | 阿里巴巴集团控股有限公司 | Video file identification method and device |
CN105430469A (en) * | 2015-11-24 | 2016-03-23 | 小米科技有限责任公司 | Method and device for playing audio/video data, terminal and server |
CN105430469B (en) * | 2015-11-24 | 2018-12-18 | 小米科技有限责任公司 | Playback method, device, terminal and the server of audio, video data |
CN105893423A (en) * | 2015-12-03 | 2016-08-24 | 乐视网信息技术(北京)股份有限公司 | Video recommendation method and system, terminal and server |
WO2017096801A1 (en) * | 2015-12-09 | 2017-06-15 | 乐视控股(北京)有限公司 | Information processing method and device |
US10440430B2 (en) | 2016-02-29 | 2019-10-08 | Gracenote, Inc. | Media channel identification with video multi-match detection and disambiguation based on audio fingerprint |
US10631049B2 (en) | 2016-02-29 | 2020-04-21 | Gracenote, Inc. | Media channel identification with video multi-match detection and disambiguation based on audio fingerprint |
CN108713321B (en) * | 2016-02-29 | 2019-06-11 | 格雷斯诺特公司 | It is identified using more matching detections with the media channel of the disambiguation based on broadcast time |
CN108702524B (en) * | 2016-02-29 | 2019-06-11 | 格雷斯诺特公司 | It is identified using more matching detections and the media channel of location-based disambiguation |
US11317142B2 (en) | 2016-02-29 | 2022-04-26 | Roku, Inc. | Media channel identification with multi-match detection and disambiguation based on location |
US10412448B2 (en) | 2016-02-29 | 2019-09-10 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on location |
US10419814B2 (en) | 2016-02-29 | 2019-09-17 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on time of broadcast |
CN108702524A (en) * | 2016-02-29 | 2018-10-23 | 格雷斯诺特公司 | It is identified using more matching detections and the media channel of location-based disambiguation |
US10524000B2 (en) | 2016-02-29 | 2019-12-31 | Gracenote, Inc. | Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference-fingerprint feature |
US10523999B2 (en) | 2016-02-29 | 2019-12-31 | Gracenote, Inc. | Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference-fingerprint feature |
US10531150B2 (en) | 2016-02-29 | 2020-01-07 | Gracenote, Inc. | Method and system for detecting and responding to changing of media channel |
CN108713321A (en) * | 2016-02-29 | 2018-10-26 | 格雷斯诺特公司 | It is identified using the more matching detections of video and the media channel of the disambiguation based on broadcast time |
US10536746B2 (en) | 2016-02-29 | 2020-01-14 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on location |
US10567835B2 (en) | 2016-02-29 | 2020-02-18 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
US10567836B2 (en) | 2016-02-29 | 2020-02-18 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
US10575052B2 (en) | 2016-02-29 | 2020-02-25 | Gracenot, Inc. | Media channel identification and action with multi-match detection based on reference stream comparison |
US11627372B2 (en) | 2016-02-29 | 2023-04-11 | Roku, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
US11336956B2 (en) | 2016-02-29 | 2022-05-17 | Roku, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
US11617009B2 (en) | 2016-02-29 | 2023-03-28 | Roku, Inc. | Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference-fingerprint feature |
US11290776B2 (en) | 2016-02-29 | 2022-03-29 | Roku, Inc. | Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference-fingerprint feature |
US11463765B2 (en) | 2016-02-29 | 2022-10-04 | Roku, Inc. | Media channel identification and action with multi-match detection based on reference stream comparison |
US11432037B2 (en) | 2016-02-29 | 2022-08-30 | Roku, Inc. | Method and system for detecting and responding to changing of media channel |
US10805673B2 (en) | 2016-02-29 | 2020-10-13 | Gracenote, Inc. | Method and system for detecting and responding to changing of media channel |
US11206447B2 (en) | 2016-02-29 | 2021-12-21 | Roku, Inc. | Media channel identification with multi-match detection and disambiguation based on time of broadcast |
US10848820B2 (en) | 2016-02-29 | 2020-11-24 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on time of broadcast |
US11412296B2 (en) | 2016-02-29 | 2022-08-09 | Roku, Inc. | Media channel identification with video multi-match detection and disambiguation based on audio fingerprint |
US10939162B2 (en) | 2016-02-29 | 2021-03-02 | Gracenote, Inc. | Media channel identification and action with multi-match detection based on reference stream comparison |
US10972786B2 (en) | 2016-02-29 | 2021-04-06 | Gracenote, Inc. | Media channel identification and action with multi-match detection and disambiguation based on matching with differential reference- fingerprint feature |
US11012743B2 (en) | 2016-02-29 | 2021-05-18 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on single-match |
US11012738B2 (en) | 2016-02-29 | 2021-05-18 | Gracenote, Inc. | Media channel identification with multi-match detection and disambiguation based on location |
US11089357B2 (en) | 2016-02-29 | 2021-08-10 | Roku, Inc. | Method and system for detecting and responding to changing of media channel |
US11089360B2 (en) | 2016-02-29 | 2021-08-10 | Gracenote, Inc. | Media channel identification with video multi-match detection and disambiguation based on audio fingerprint |
WO2018000642A1 (en) * | 2016-06-29 | 2018-01-04 | 乐视控股(北京)有限公司 | Method, terminal and server for identifying program channel |
CN108271073A (en) * | 2016-12-28 | 2018-07-10 | 上海昕丝文化传播有限公司 | SDK flow chart of data processing |
CN110113677A (en) * | 2018-02-01 | 2019-08-09 | 阿里巴巴集团控股有限公司 | The generation method and device of video subject |
CN108566562A (en) * | 2018-05-02 | 2018-09-21 | 中广热点云科技有限公司 | Copyright video information structuring arranges the method for completing sample approved sample |
CN108566562B (en) * | 2018-05-02 | 2020-09-08 | 中广热点云科技有限公司 | Method for finishing sample sealing by copyright video information structured arrangement |
CN111193946A (en) * | 2018-11-15 | 2020-05-22 | 北京盛世辉科技有限公司 | Network interaction control terminal, network interaction system and network interaction communication method |
CN110913241B (en) * | 2019-11-01 | 2022-09-30 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
CN110913241A (en) * | 2019-11-01 | 2020-03-24 | 北京奇艺世纪科技有限公司 | Video retrieval method and device, electronic equipment and storage medium |
CN111614991A (en) * | 2020-05-09 | 2020-09-01 | 咪咕文化科技有限公司 | Video progress determination method and device, electronic equipment and storage medium |
CN112203139A (en) * | 2020-10-12 | 2021-01-08 | 广州欢网科技有限责任公司 | Program content identification method and intelligent system of intelligent television |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103581705A (en) | Method and system for recognizing video program | |
CN202998337U (en) | Video program identification system | |
CN110134829B (en) | Video positioning method and device, storage medium and electronic device | |
CN108366278B (en) | User interaction implementation method and device in video playing | |
CN104754413B (en) | Method and apparatus for identifying television signals and recommending information based on image search | |
CN110198432B (en) | Video data processing method and device, computer readable medium and electronic equipment | |
CN104618803B (en) | Information-pushing method, device, terminal and server | |
CN102868934B (en) | Video object information search method and device based on intelligent television | |
CN102223581B (en) | Video program searching method and video playing terminal | |
US20120272279A1 (en) | Apparatus for providing internet protocol television broadcasting contents, user terminal and method for providing internet protocol television broadcasting contents information | |
CN109981695B (en) | Content pushing method, device and equipment | |
WO2014032420A1 (en) | Method and system for obtaining interaction information | |
CN104994426A (en) | Method and system of program video recognition | |
WO2016192501A1 (en) | Video search method and apparatus | |
KR20150083355A (en) | Augmented media service providing method, apparatus thereof, and system thereof | |
CN104506946A (en) | Television program identification method based on image identification and system thereof | |
CN103607635A (en) | Method, device and terminal for caption identification | |
CN103945234A (en) | Video-related information providing method and device | |
CN108881119B (en) | Method, device and system for video concentration | |
CN103368925A (en) | Device authentication method | |
CN111444822B (en) | Object recognition method and device, storage medium and electronic device | |
KR20200077176A (en) | Apparatus and method for recommending keyword related to video | |
CN111274449A (en) | Video playing method and device, electronic equipment and storage medium | |
KR101933696B1 (en) | Vod service system based on ai video learning platform | |
CN111263183A (en) | Singing state identification method and singing state identification device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140212 |
|
RJ01 | Rejection of invention patent application after publication |