CN105052161A - Systems and methods for real-time television ad detection using an automated content recognition database - Google Patents

Systems and methods for real-time television ad detection using an automated content recognition database Download PDF

Info

Publication number
CN105052161A
CN105052161A CN201480015936.XA CN201480015936A CN105052161A CN 105052161 A CN105052161 A CN 105052161A CN 201480015936 A CN201480015936 A CN 201480015936A CN 105052161 A CN105052161 A CN 105052161A
Authority
CN
China
Prior art keywords
frame
candidate segment
data
data storage
stored
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.)
Granted
Application number
CN201480015936.XA
Other languages
Chinese (zh)
Other versions
CN105052161B (en
Inventor
泽夫·纽梅尔
布莱恩·里德
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Granville Construction Technology Co Ltd
Original Assignee
Individual
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from US14/089,003 external-priority patent/US8898714B2/en
Application filed by Individual filed Critical Individual
Priority to CN201811471681.4A priority Critical patent/CN109905726B/en
Priority claimed from US14/217,075 external-priority patent/US9055309B2/en
Priority claimed from PCT/US2014/030782 external-priority patent/WO2014145929A1/en
Priority claimed from PCT/US2014/030805 external-priority patent/WO2014145947A1/en
Publication of CN105052161A publication Critical patent/CN105052161A/en
Application granted granted Critical
Publication of CN105052161B publication Critical patent/CN105052161B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/254—Management at additional data server, e.g. shopping server, rights management server
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11B—INFORMATION STORAGE BASED ON RELATIVE MOVEMENT BETWEEN RECORD CARRIER AND TRANSDUCER
    • G11B27/00—Editing; Indexing; Addressing; Timing or synchronising; Monitoring; Measuring tape travel
    • G11B27/02—Editing, e.g. varying the order of information signals recorded on, or reproduced from, record carriers
    • G11B27/031—Electronic editing of digitised analogue information signals, e.g. audio or video signals
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/35—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users
    • H04H60/37—Arrangements for identifying or recognising characteristics with a direct linkage to broadcast information or to broadcast space-time, e.g. for identifying broadcast stations or for identifying users for identifying segments of broadcast information, e.g. scenes or extracting programme ID
    • H04H60/375—Commercial
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04H—BROADCAST COMMUNICATION
    • H04H60/00—Arrangements for broadcast applications with a direct linking to broadcast information or broadcast space-time; Broadcast-related systems
    • H04H60/56—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54
    • H04H60/59—Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54 of video
    • 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
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2668—Creating a channel for a dedicated end-user group, e.g. insertion of targeted commercials based on end-user profiles
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/81—Monomedia components thereof
    • H04N21/812—Monomedia components thereof involving advertisement data
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/835—Generation of protective data, e.g. certificates
    • H04N21/8358—Generation of protective data, e.g. certificates involving watermark

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Computer Security & Cryptography (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)

Abstract

A system and method for the automated real-time detection and processing of commercial messages, public service announcements or similar short-duration, repeated TV programing segments occurring in one or more broadcast video steams is described. A process is utilized that identifies possible commercial segments by identifying discrete video segments that have specific short durations among other attributes. Video segments that appear to have these characteristics are considered likely to be television commercials, promotions, or public service announcements and are stored in a TV Ad database which is separate from the primary television content database. Incoming video from a plurality of television programming sources is process into fingerprints and placed in a master TV content database. At the same time, said incoming programming is tested for matches in a TV ad database. If a match is found, then the presumed TV ad is removed from the master content database.

Description

For using the system and method for the real-time television purposes of commercial detection in automation content identification data storehouse
Inventor
Ze Funiu Mel (ZeevNeumeier)
Brian Reed (BrianReed)
Priority request
The application forms submission on May 27th, 2010, and on November 6th, 2013 presses U.S. Patent number 8,595,781 U.S. Patent Application No. 12/788 being entitled as " METHODSFORIDENTIFYINGVIDEOSEGMENTSANDDISPLAYINGCONTEXTUA LTARGETEDCONTENTONACONNECTEDTELEVISION (for identifying video segment and connecting method TV showing context object content) " issued, the part continuation application of 721, that application is the U.S. Provisional Patent Application being entitled as " SYSTEMFORPROCESSINGCONTENTINFORMATIONINATELEVIDEOSIGNAL (system for the treatment of the content information in television video frequency signal) " submitted in requirement on May 29th, 2009 number 61/182, the non-provisional application of the rights and interests of 334, and be the U.S. Provisional Patent Application being entitled as " CONTEXTUALTARGETINGBASEDONDATARECEIVEDFROMATELEVISIONSYS TEM (the context target based on the data received from television system is determined) " submitted in requirement on December 29th, 2009 number 61/290, the non-provisional application of the rights and interests of 714, the application forms the part continuation application being entitled as the U.S. Patent Application No. 12/788,748 of " METHODSFORDISPLAYINGCONTEXTUALLYTARGETEDCONTENTONACONNEC TEDTELEVISION (for connecting method TV showing the content being based on context decided to be target) " submitted on May 27th, 2010 further, the application form further submit on November 25th, 2013 be entitled as " _ _ _ _ _ _ _ _ _ _ _ _ _ " the part continuation application of U.S. Patent Application No. 14/089,003, the application forms the U.S. Patent Application No. * */* * * being entitled as " SYSTEMSANDMETHODSFORADDRESSINGAMEDIADATABASEUSINGDISTANC EASSOCIATIVEHASHING (for service range relevance hashing to the system and method for media database addressing) " submitted on March 17th, 2014 further, the part continuation application of * * *, the application forms the U.S. Patent Application No. * */* * * being entitled as " SYSTEMSANDMETHODSFORIDENTIFYINGVIDEOSEGMENTSFORDISPLAYIN GCONTEXTUALLYRELEVANTCONTENT (for identifying video segment to show the system and method for contextual content) " submitted on March 17th, 2014 further, the part continuation application of * * *, the application forms the U.S. Patent Application No. * */* * * being entitled as " SYSTEMSANDMETHODSFORON-SCREENGRAPHICSDETECTION the system and method for test pattern (on the screen) " submitted on March 17th, 2014 further, the part continuation application of * * *, the application forms the U.S. Patent Application No. * */* * * being entitled as " SYSTEMSANDMETHODSFORIMPROVINGSERVERANDCLIENTPERFORMANCEI NFINGERPRINTACRSYSTEMS (system and method for improvement of the server and client side's performance in fingerprint ACR system) " submitted on March 17th, 2014 further, the part continuation application of * * *, the application forms the U.S. Patent Application No. * */* * * being entitled as " SYSTEMSANDMETHODSFORMULTI-BROADCASTDIFFERENTIATION (system and method for multi-broadcast is distinguished) " submitted on March 17th, 2014 further, the part continuation application of * * *, and the application forms the part continuation application being entitled as the U.S. Patent Application No. 61/791,578 of " SYSTEMSANDMETHODSFORIDENTIFYINGVIDEOSEGMENTSBEINGDISPLAY EDONREMOTELYLOCATEDTELEVISIONS (for being identified at the system and method for the video segment that long range positioning TV shows) " submitted on March 15th, 2013 further, aforementioned application or current CO-PENDING or the application of the rights and interests of having the right to enjoy the submission date of current CO-PENDING application.
Invention field
Present invention relates in general to image recognition, and relate more specifically to the system and method for the real-time television purposes of commercial detection for using automation content identification data storehouse.
Background
The Aulomatizeted Detect of television commercial is the very interested field of different supporter for a long time.Many consumers wish to seek certain mode always makes whole commercial advertisement quiet or even skip, and is particularly being recorded in the program for time shift viewing.Propose the many solutions for this needs and all run in consumer device level and relate to and once identify a commercial advertisement when commercial advertisement occurs in the broadcast video stream watched or record.
Other use this automation contents recognizing technology to be those sides that every that needs the commercial advertisement of checking specific TV in fact as contracted in many channels, time slot and market is broadcasted.In addition, which advertisement other companies are playing to which company and investigate and collect statistics in which market.Notebook data can be used for company oneself use or for reselling.Meanwhile, other companies investigation commercial advertisement comes for the more effective advertisement of client development.The analysis of these types usually completes by market grade and needs to monitor a large amount of channel and market.
Since half a century in past, this commercial advertisement checking or collection procedure are manually performed by the mankind during airtime according to plan, or visually search for tape that (F.F., rewinding etc.) broadcast in the early time or other records perform.As can be appreciated, wait for commercial advertisement play (broadcast), set up recording equipment come recorded announce and/or search broadcasted content record to verify commercial content broadcasting can be time-consuming, require great effort and the task of costliness.Therefore, there are a kind of needs be not satisfied: Aulomatizeted Detect and the identification procedure of optimizing the business information in live video stream.
Because almost the consumer of each market segment can use the wired system and satellite system that transmit hundreds of program channels now simultaneously, mark, checking and the tracking ability which commercial advertisement is being broadcasted in which market at any given time propose the calculating challenge be not of the common run.The state of the art is mainly absorbed in mark view single (site) equipment (as television set) always and when is presented commercial advertisement.Known to those skilled in the art, enable they simultaneously Real-Time Monitoring hundreds of video flowings computing power and carrying cost are commercially reasonably expanded (scaling) method simultaneously and remain unsatisfied needs.
General introduction
In certain embodiments, the illustrative methods relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse can comprise: absorb at least one audiovisual streams, comprises at least some data be associated with one or more frames of this audiovisual streams to major general and is stored in a program content data memory; Determine a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this; And test this candidate segment determined at least one occurrence in a known advertisement data storage, and if test to return at least one occurrence in this known advertisement data storage to this candidate segment, then remove from this program content data memory at least some data that major general is associated with this candidate segment.
In certain embodiments, the illustrative methods relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse may further include: test this candidate segment determined at least one occurrence in this program content data memory, and if test returns at least one occurrence in this program content data memory to this candidate segment, at least some data be then associated to major general with this candidate segment remove and at least some data be associated with this candidate segment are stored in this known advertisement data storage from this program content data memory.
In certain embodiments, determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) can comprise: the one or more instructions receiving a frame to this absorbed stream of audiovisual data; Analyze this one or more instruction to a frame, comprise and at least determine this one or morely indicates whether it may is a start frame of a candidate segment; If determine a start frame, then whether analyze the one or more frames received after this start frame, comprising one of this one or more frame at least determining to receive after this start frame may be an end frame; And if determine an end frame, then set up this one or more frame and (iii) this end frame that (i) this start frame, (ii) receive after this start frame and before this end frame as this candidate segment.
In certain embodiments, analyze this one or more instruction of a frame (comprise at least determine these one or more indicate whether it may is a start frame of a candidate segment) and analyze the one or more frames (comprising whether the frame at least determining to receive after this start frame may be an end frame) received after this start frame and can comprise: determine at least one item whether a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, and if at least one item that a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, then set up this frame as at least one item in a start frame or an end frame.
In certain embodiments, determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) can comprise: the one or more instructions receiving a frame to this absorbed stream of audiovisual data; The data be associated with the frame end received recently coherent picked-up frame sequence and the data be associated with the one or more consecutive frames sequences be stored in before in this program content data memory are compared; And provide the one or more instructions to the one or more consecutive frames sequences be stored in before in this program content data memory based on this comparing data at least in part.
In certain embodiments, determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) may further include for each frame sequence in this indicated one or more consecutive frames sequence, determine whether this consecutive frames sequence is an advertisement.In certain embodiments, determine whether this consecutive frames sequence is that an advertisement can comprise: at least one item in number of seconds length and the frame count that is associated with this consecutive frames sequence is assessed, and if number of seconds length or frame count are substantially similar to a standard advertisement length, then set up this consecutive frames sequence as a candidate segment.In certain embodiments, and if assess number of seconds length or frame count at least one item in number of seconds length and the frame count that is associated with this consecutive frames sequence to be substantially similar to a standard advertisement length and then to set up this consecutive frames sequence and may further include as a candidate segment: adjust and mate at least one threshold value be associated, with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated; Based at least one adjusted threshold value, this candidate segment is mated with this one or more consecutive frames sequence be stored in before in this data storage at least in part; And if at least in part based at least one adjusted threshold value, this candidate segment and this one or more consecutive frames sequences match be stored in before in this data storage, then determine starting point and the end point of this candidate segment.
In certain embodiments, adjust at least one threshold value (with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated) be associated with coupling can comprise: adjust at least one radius be associated with a path tracing algorithm, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.In certain embodiments, adjust at least one threshold value (with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated) be associated to coupling can comprise: adjust and at least one duration relevant with at least one case (bin) that a path tracing algorithm is associated, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.
In certain embodiments, determine that the starting point of this candidate segment and end point can comprise: adjust and mate at least one threshold value be associated, with returning of comparatively high amts, this at least one threshold value adjusted suspects that item is associated; One or more instructions that the one or more instruction be associated with each frame in this candidate segment is associated with a respective frame in this one or more consecutive frames sequence be stored in before in this data storage compared, this is more at least in part based on this adjusted at least one threshold value; And relatively test each frame in this candidate segment based on this at least in part and be stored in the inconsistency between a respective frame in this one or more consecutive frames sequence in this data storage before.
In certain embodiments, if relatively test each frame in this candidate segment and the inconsistency between a respective frame in this one or more consecutive frames sequence be stored in before in this data storage and can comprise any frame in this candidate segment being stored in before in this one or more consecutive frames sequence in this data storage based on this not there is a corresponding occurrence at least in part, then the frame of corresponding for the neither one in this candidate segment occurrence is removed from this one or more consecutive frames sequence be stored in before this data storage.In certain embodiments, if each frame relatively tested in this candidate segment based on this at least in part does not have a corresponding occurrence to any frame that the inconsistency between a respective frame in this one or more consecutive frames sequence be stored in before in this data storage can comprise in this one or more consecutive frames sequence be stored in before in this data storage in this candidate segment, then add this frame in this one or more consecutive frames sequence be stored in before in this data storage to this candidate segment.In certain embodiments, each frame relatively tested in this candidate segment based on this at least in part can comprise with the inconsistency between a respective frame in this one or more consecutive frames sequence be stored in before in this data storage: compare the inconsistency between a respective frame in each frame tested in this candidate segment and this one or more consecutive frames sequence be stored in before in this data storage at least in part based on this; And remedy any inconsistency found by test, this remedies the border that can be used to identification of candidate item.
In certain embodiments, absorb at least one audiovisual streams (comprising at least some data be associated with one or more frames of this audiovisual streams to major general to be stored in a program content data memory) and and if test this candidate segment determined at least one occurrence in a known advertisement data storage and test this candidate segment and return at least some data that at least one occurrence in this known advertisement data storage is then associated with this candidate segment to major general and remove and can comprise from this program content data memory: absorb at least two audiovisual streams, comprising at least some data that the one or more frames at least one audiovisual streams in major general and this at least two audiovisual streams are associated is stored in a program content data memory, this at least some data comprise to from wherein receive to the audiovisual streams of this one or more frame at least one instruction, and test this candidate segment determined at least one occurrence in a known advertisement data storage, and if test returns at least one occurrence in this known advertisement data storage to this candidate segment, at least some data be then associated to major general with this candidate segment remove from this program content data memory.
In certain embodiments, determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) can comprise and confirm that this candidate segment has a Low threshold coupling based at least one duration of a candidate segment at least in part; And with mating of a known advertisement, the one or more fingerprint at least in part based on this candidate segment confirms that this candidate segment has a high threshold and mates.In certain embodiments, determine a candidate segment (this candidate segment to comprise from this at least one or more successive frame of audiovisual streams of at least one picked-up) can comprise determine it can is advertisement, commercial advertisement, public service bulletin, publicity, the time spot at least partially, advertisement pod at least partially or the fragment of at least one be about in the TV programme publicity that presents.In certain embodiments, determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) can comprise and determine a candidate segment, this candidate segment comprises at least one or more successive video frames of the audiovisual streams of at least one picked-up from this.
In certain embodiments, the illustrative computer program product relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse can comprise at least one non-transient computer-readable medium, and this at least one non-transient computer-readable medium can comprising: for absorbing one or more instructions of at least one audiovisual streams, comprising at least some data be associated with one or more frames of this audiovisual streams to major general and being stored in a program content data memory; For determining one or more instructions of a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this; And and if for testing one or more instructions that at least one occurrence test of a determined candidate segment in a known advertisement data storage removes from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated to major general with this candidate segment.
In certain embodiments, the example system relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse can comprise the circuit being configured for and absorbing at least one audiovisual streams, comprises at least some data be associated with one or more frames of this audiovisual streams to major general and is stored in a program content data memory; Be configured for the circuit determining a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams from least one picked-up; And and if be configured for the circuit tested at least one occurrence test of a determined candidate segment in a known advertisement data storage and remove from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated with this candidate segment to major general.
In addition to the foregoing, in the text (such as, accompanying drawing and/or detailed description) of such as this disclosure and/or teaching middle elaboration and describing different additive methods, system and/or program product embodiment of accompanying drawing.
Foregoing teachings is general introduction and therefore must comprises the simplification of details, summary and omission; Therefore, it will be understood by those skilled in the art that general introduction is only illustrative and be not intended to limit by any way.Other aspects of device described here and/or process and/or other themes, embodiment, feature and advantage will become obvious in set forth herein teaching.
Brief Description Of Drawings
With reference to the following drawings, below describe in further detail some embodiment of the present invention.
Fig. 1 illustrates the typical time spot (or advertisement pod (adpod)) in time scale, is highlighted and how can intercuts commercial message.If the duration of commercial advertisement falls in some parameter (104 Low threshold), first commercial advertisement can be detected, and if suspect the fingerprint matching of certain the existing commercial advertisement in fragment and database 135, then be identified with high confidence level.
How mutual each assembly that Fig. 2 illustrates system is, thus enable the independent database of TV programme and commercial message be set up by the mode of the reliable mark in real time that can realize advertisement information, safeguard and utilize.
Fig. 3 illustrates flow chart, and how interrelated the order summarizing each step of the method is with them.
Fig. 4 illustrates prior art flow chart.
Fig. 5 illustrates operating process, and this flow process represents the exemplary operations relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse.
Fig. 6 illustrates the alternate embodiment of the operating process of Fig. 5.
Fig. 7 illustrates the alternate embodiment of the operating process of Fig. 5.
Fig. 8 illustrates the alternate embodiment of the operating process of Fig. 5.
Fig. 9 illustrates the alternate embodiment of the operating process of Fig. 5.
Figure 10 illustrates the alternate embodiment of the operating process of Fig. 5.
Figure 11 illustrates the alternate embodiment of the operating process of Fig. 5.
Figure 12 illustrates illustrative computer program product.
Figure 13 illustrates the system relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse.
Describe in detail
There is described herein the system and method that a kind of commercial message for occurring in one or more broadcast video stream, public service bulletin or the similar automation of television program segment that is long, that repeat in short-term detect in real time and process.Make use of a kind of process being identified possible commercial advertisement fragment by the mark specific discrete video fragment long in short-term had except other attributes.The video segment seeming to have these features is probably considered to television commercial, publicity or public service bulletin and is stored in the television advertising database separated with main television content database.The video that imports into from multiple tv programme source is processed into fingerprint and is placed in main television content database.Meanwhile, the occurrence of program in television advertising database is imported described in test into.If discovery occurrence, then inferred television advertising is removed from main contents database.If do not find occurrence, then import video into according to the test of independent television advertising database.If find occurrence in television advertising database, then video segment is removed from main television content database.This high efficiency method enables system by known frequent repetition and removes across the television advertising material being permitted multichannel high redundancy.This detection the process removing television advertising from main television content database decrease the wrong report number of matches of major television content and improve the systematic function of video matching system.
Present invention relates in general to video frequency signal processing, and relate more specifically to for the treatment of multiple broadcast video signal stream to identify, extract and to analyze the technology of the video content of commercial advertisement or its particular type, the video content of these types is shared some feature or has the signature mated with contents known.System for realizing described method is made up of a series of software process run on computer server.This server comprises microprocessor, database, input equipment and output equipment, and wherein, described database comprises and being stored in read-only storage or other digital storage systems and the computer-readable instruction that can be performed by described microprocessor.
Safeguard that one of the problem in the video fingerprint data storehouse of automation content recognition (ACR) system is to comprise a high proportion of television commercial from the content of live television broadcast picked-up.With regard to its essence, commercial advertisement repeats and many example Fast Fillings reference (coupling) databases of the described same content of described content.Fig. 1 illustrates the typical programme channel 106 with the time spot 109 (being called as in TV industry " advertisement pod (adpod) "), except other materials, time spot channel generally includes the fragment of many different lengths: the program promotional presented is announced and be about to television advertising, public service.The duration of typical television advertising 107 is 30 seconds.The duration of typical TV programme publicity is 15 seconds.The total length of advertisement pod 139 is usually from total duration change of 60 seconds to three minutes.Advertisement pod and other non-program materials occupy average TV programme hour more than 33%.
The content of this large amount of repetition can cause ACR system produce a large amount of wrong report coupling or can't find coupling on the contrary at all.In one case, this is because the repetition of concrete commercial advertisement in many different TV programme on the repetition of commercial advertisement in same TV programme process and many different television channels.Therefore, when the video source of the unknown comprises television commercial fingerprint (clue), the database with television commercial at high proportion will produce proportional with the repetition percentage of described commercial advertisement manyly to mate in whole database, thus produces useless result in the commercial advertisement duration of repetition.
But existing problems when determining whether two fingerprints of the repetition in reference database repeat like this, because they should uncared-for minuent mate with content matching or because they represent.In order to alleviate this problem, invention describes a kind of algorithm detecting commercial advertisement and other video segments (program promotional presented as being about to) frequently repeated.The length when basic premise of this algorithm is commercial advertisement, given television channel repeats many times and repeats across multiple television channel.
Once video segment is marked as commercial advertisement, it will be stripped and be stored in independent television commerce database from master data base.Except clearing up main TV program database, this also can detect particular commercial and not will their independent loads to the useful feature in main advertising database.
Television advertising testing process works as follows: as seen in Fig. 2, and TV programme is fed through 202 to be uploaded, process and output in main matching system database 204 and be sent to television commerce video detector 203.For each television channel of the present invention's monitoring, there is the example of television commercial detector of the present invention.
Television commercial detector runs content search process to the usual input feeding with central service apparatus location of the present invention.This with of the present invention user household to be connected the process run in TV similar, wherein said invention with fixing per time interval sample number from one or more screen positions read pixel spacing.The same with domestic. applications, described process is input to the process of described pel spacing combine digital will attempts the content matching system of being mated with contents known database by described picture element matrix to prepare described spacing further.
Different from the application run on the TV enabled of the present invention, commercial detector content search process continues each possibility matching of search until reach matching threshold and that coupling aggregation process stopping.The difference that this and regular content are searched for is, usually, the content search returning multiple occurrence is considered to invalid, because the fragment of regular length does not repeat in the body interior of TV programme usually.This advertisement search process run continuously and check from each tv programme source, the video that is fed to system of the present invention.
For each possible occurrence returned from said process, trigger following process asynchronously, allow the above-mentioned algorithm following process simultaneously that continues to search for perform in three steps:
Step 1: the length assessing each possible occurrence, this length should be longer than given threshold value, such as, 5 seconds, and be less than another threshold value, be perhaps 60 seconds.In FIG, this is duration as shown in 109 and Low threshold coupling 101.In fact, according to such as at United States Patent (USP) 8,585, the method disclosed in 781, this is only the difference between first match point around predetermined threshold 104 of fragment and the timestamp of last match point.
Step 2: coupling is if possible tested in the accepted parameter of (step 1) at last item, then it is again through content search, but test request is refinement more, wherein perform same search with the same before, but need the more close match in the point (fingerprint) and 105 of two samples.Assess the result of this test, and if the percentage of the point (fingerprint) of search coupling stricter is therewith less than given threshold value, then possible coupling is cancelled.
Step 3: the test before fitting through if possible, then it is through another content search again, but configures much loose, that is, search is with identical before, but allows each some interval of two samples farther, perhaps the time or apart from least one item on.Result of this test helps to identify the border of television commercial suspected and does not evaluatedly have missing point (namely, in two samples a little all mate) and the beginning boundary had in the time threshold of the initial commercial advertisement suspected and terminate boundary (namely, if coupling possible be at first 15 seconds long, then the result of loose content search can not be 30 seconds long etc.).
With reference to Figure 12, if the video segment sample of the unknown is by all three tests above, then think that it is television commercial, publicity, board service bulletin, and the information defining described video segment is sent to video segment processor 207 by 206.Mate if described sample is announced with the television commercial existed in advertising database 205, publicity or board service, then new example removes from main TV program database 204 and does not need the advertisement of described coupling to be again placed on advertising database by video segment processor 207.If described sample mates with main content of TV program, then that fragment (unknown fragment is in period coupling) of TV programme is considered to advertisement, and enter match advertisements two examples existed in the new program of system and TV data storehouse 204 to be all removed, and on their position, new commercial advertisement is being input in advertising database 205.
The flow chart summarizing the method is presented in Fig. 3.Each television video stream or " channel " are accepted by system 301 and are initially tested according to existing known commercial advertising database 303.If there is coupling 304, then it is removed 308 from TV program database.If coupling, then do not carry out test 307 according to known TV program database 308 to it.If its coupling, then video segment coupling, then remove 310 by it from TV program database 310 and be added into television commercial database 311.If its coupling, then think that it is not associated clip 312 and is left in the basket.Fig. 4 illustrates prior art flow chart for comparing.
Fig. 5 illustrates operating process 500, and this flow process represents the exemplary operations relevant to using the real-time television purposes of commercial detection in automation content identification data storehouse.In Figure 5 and in the figure below of each example comprising operating process, the above-mentioned example about Fig. 1 to Fig. 3 and/or provide about other examples and context is discussed and explaination.However, it should be understood that and can perform these operating processes in other environment many and context and/or at Fig. 1 to Fig. 3 in revision.And, although present each operations flows with illustrated sequence, should be understood that can perform each by other orders different from illustrated order operates, or these operations can be performed simultaneously.
After a start operation, operating process 500 moves to operation 502.Operation 502 depicts at least one audiovisual streams of picked-up, comprises at least some data be associated with one or more frames of this audiovisual streams to major general and is stored in program content data memory.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, comprise importing stream of audiovisual data into and can being transmitted to ground by the satellite that data flow is transferred to from national network broadcasting channel center of program and ad content.Can also receive from other sources (such as, by transmitting to ground from other sources), being received by Fiber connection, use conventional VHF, UHF or microwave antenna to receive, by receiving data streams such as data networks (as the Internet).The data be associated with data flow can be stored in the media data storage that also can be called as main matching system database.
The data be associated with data flow by it operation that can be stored in media data storage can comprise the operation described in following father's patent application: U.S. Patent Application No. 12/788,721 (is United States Patent (USP) 8 now, 595,781) " METHODSFORIDENTIFYINGVIDEOSEGMENTSANDDISPLAYINGCONTEXTUA LTARGETEDCONTENTONACONNECTEDTELEVISION (for identifying video segment and connecting method TV showing context object content) " (' 781 patent); And/or the related U.S. patent application number * */* * * simultaneously to submit to instant application, * * " SYSTEMSANDMETHODSFORADDRESSINGAMEDIADATABASEUSINGDISTANC EASSOCIATIVEHASHING (for service range relevance hashing to the system and method for media database addressing) " and/or related application * */* * *, * * * " SYSTEMSANDMETHODSFORIDENTIFYINGVIDEOSEGMENTSFORDISPLAYIN GCONTEXTUALLYRELEVANTCONTENT (for identifying video segment so that based on context display is decided to be the system and method for the content of target) " (" related application ").
Next, operation 504 depicts determines a candidate segment, and this candidate segment comprises at least one or more successive frame in the audiovisual streams of at least one picked-up from this.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, after picked-up stream of audiovisual data, perhaps by being fed to the content search process of carrying out selecting possible occurrence to importing into.Possible occurrence can represent any consecutive frames fragment of picked-up in any channel feeding just in similar for it or identical consecutive frames fragment Already in media content database.Possible occurrence can represent relevant advertisement or another relevant short-movie section, as public service bulletin.Then possible occurrence can be assessed by three step process, this process can comprise the possible occurrence of assessment length, use stricter coupling to require closely to spend with the fingerprint of possible the occurrence of existing frame fragment and use so not strict mating to require to assess and the fingerprint of possible occurrence of existing frame is spent closely, thus help identifies the border of possible occurrence.Possible occurrence alternatively fragment is returned.
Next, operation 506 depicts the determined candidate segment of test at least one occurrence in known advertisement data storage, and if test to return at least one occurrence in this known advertisement data storage to this candidate segment, then remove from program content data memory at least some data that major general is associated with this candidate segment.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, if the data be associated with candidate segment with and be stored in the Data Matching that the known advertisement in advertising database is associated, then the data be associated with the candidate segment be ingested are removed from media content database.Then, this operating process can proceed to end operation.
Fig. 5 also illustrates the alternate embodiment of example operational flow 500.Fig. 5 illustrates example embodiment, and wherein operating process 500 can comprise at least one additional operations 508.
Operation 508 illustrates the determined candidate segment of test at least one occurrence in program content data memory, and if test returns at least one occurrence in this program content data memory to this candidate segment, then at least some data be associated to major general with this candidate segment remove and at least some data be associated with this candidate segment are stored in this known advertisement data storage from this program content data memory.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, if the result of operation 506 is by not knowing that under a cloud is the candidate segment of advertisement, then according to the data that media content database inspection is associated with this candidate segment before checking database.If also find in media content database that suspection is the candidate segment of advertisement, then the data be associated with this fragment found in media content database are removed.Further, the data be associated with this fragment are placed in known advertisement data storage.Then, this operating process can proceed to end operation.
Fig. 6 illustrates the alternate embodiment of the example operational flow 500 of Fig. 5.Fig. 6 illustrates example embodiment, wherein operates 502 and can comprise at least one additional operations.Additional operations can comprise operation 602, operation 604, operation 606 and/or operation 608.
Operation 602 illustrates the one or more instructions received the frame in absorbed stream of audiovisual data.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, the data be associated with from the concrete frame importing data flow into are selected.
Further, operation 604 illustrates analyzes one or more instructions to frame, comprises and at least determines this one or morely indicates whether it may is the start frame of candidate segment.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, can check whether the data be associated with concrete frame exist and concrete frame will be indicated may to be the concrete signature of the beginning of commercial advertisement.
Further, if operation 606 illustrates determine start frame, then whether analyze the one or more frames received after this start frame, comprising one of this one or more frame at least determining to receive after this start frame may be end frame.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, if detect that signature shows that this frame may be the first frame of commercial advertisement, then this process starts to analyze the successive frames that receives after claimed start frame to check whether any frame in these successive frames may comprise concrete signature.
Further, if operation 608 illustrates and determines end frame, then set up (i) this start frame, this one or more frame that (ii) receives after this start frame and before this end frame and (iii) this end frame be as this candidate segment.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, when determining claimed start frame and end frame, those frames and all intermediate frames linked together can be candidate segment.
Further, Fig. 6 illustrates the further alternate embodiment of operation 604.Operation 604 can comprise at least one additional operations 610.
Operation 610 illustrates at least one item determining whether a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, and if at least one item that a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, then set up this frame as at least one item in a start frame or an end frame.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, show that frame may be that to comprise that frame be monochromatic (such as, black, pure white) for the signature of start frame, because commercial advertisement often starts with such as one or more entirely black frame.Alternately, the start frame of commercial advertisement can be represented by " scene changes ".In other words, two programs in succession before commercial advertisement or commercial advertisement probably comprise different scenes.When content and the content of previous frame of frame remarkable different time, it can indicate scene changes, and this can represent the conversion between conversion from program to commercial advertisement or commercial advertisement.The remarkable difference detected between two frames can have been come by the one or more operation disclosed in ' 781 patent and/or related application at least in part.Notably, scene changes does not determine commercial advertisement separately, and is only that this frame may represent start frame.Other operations described here can help to continue assessment by the fragment whether commercial advertisement of first frame identification with scene changes, thus, even if scene changes represents in program from a scene to the change of another scene, instead of the change from program to commercial advertisement, test is after a while cancelled making using the fragment started as the scene changes of commercial advertisement.
Can also be applied to about the same signature described by operation 610 and determine that whether frame can be the end frame in operation 606.
Fig. 7 illustrates the alternate embodiment of example operational flow 500.Fig. 7 illustrates example embodiment, wherein operates 504 and can comprise at least one additional operations.Additional operations can comprise operation 702, operation 704, operation 706 and/or operation 708.
Operation 702 illustrates the one or more instructions received the frame in absorbed stream of audiovisual data.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, the data be associated with from the concrete frame importing data flow into are selected.
Further, operate 704 to illustrate the data be associated with the frame end received recently coherent picked-up frame sequence and the data be associated with the one or more consecutive frames sequences be stored in before in this program content data memory are compared.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, according to media content data memory pair be ingested and with the data inspection that the consecutive frames fragment of concrete frame end is associated determine whether to have in this data storage can with just to absorb and with any consecutive frames fragment of the fragment match of concrete frame end.
Further, operation 706 illustrates and provides the one or more instructions to the one or more consecutive frames sequences be stored in before in this program content data memory based on this comparing data at least in part.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, matching operation 704 can return the data be associated with the coherent fragment of one or more at least part of coupling.The consecutive frames fragment just absorbed with the one or more consecutive frames fragments in media content database mate or semi-match can indicate the consecutive frames fragment just absorbed may be commercial advertisement.Thus, also may be one or more consecutive frames fragments of mating at least partly in media content database.Importantly, for performance reason, matching operation not searching media content data base obtains lucky frame by frame with by pixel matching.But, return the coupling suspected relevant at least partly to the fragment just absorbed from media content database, perhaps undertaken mating and/or returning by the operation disclosed in ' 781 patent and/or related application.
Further, operation 708 illustrates for each frame sequence in this indicated one or more consecutive frames sequence, determines whether this consecutive frames sequence is advertisement.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, one or more test can be applied to consecutive frames sequence, this consecutive frames sequence this stage be the advertisement suspecting or claim, apply this one or more test to confirm that this consecutive frames sequence is suspecting of advertisement.
Further, Fig. 7 illustrates the further alternate embodiment of operation 708.Operation 708 can comprise at least one additional operations 710.
Operation 710 illustrates to be assessed at least one item in number of seconds length and the frame count that is associated with this consecutive frames sequence, and if number of seconds length or frame count are substantially similar to a standard advertisement length, then set up this consecutive frames sequence as a candidate segment.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, the length of the consecutive frames sequence representing the advertisement claimed is checked.If length is close to common Ad Length (such as, 30 seconds, 15 seconds, 60 seconds or other common Ad Length), then this consecutive frames sequence still can be considered to suspected advertisement.If length keeps off common Ad Length (such as, 52 seconds), then this consecutive frames sequence is considered to is unlikely advertisement and/or is no longer considered to advertisement.Alternately, if the quantity of the frame in consecutive frames sequence is close to the quantity of frame conventional in advertisement, then this consecutive frames sequence still can be considered to suspected advertisement.The quantity of common frame can be such as 30 second time 29.997 frames per second, or roughly 900 frames.The length tested can be duration or the quantity of frame conventional in advertisement just, or can close to the duration of frame conventional in advertisement or quantity (such as, in two seconds or three seconds, or in 60-90 frame).Matching algorithm for returning candidate item from media content database can return not there is lucky identical coherent length candidate item (such as, they can be coherent fragment start or at the end of disappearance frame, or perhaps can be included in coherent fragment to start or the extra frame of end, be due to the invoked matching process that can comprise such as path tracing and/or PPLEB).Operation 710 can represent that other local steps 1 disclosed at least partially herein.
Fig. 8 illustrates operating process 800, and this operating process represents the exemplary operations of the example operational flow 500 proceeding Fig. 5.Operating process 800 can comprise operation 802, operation 804 and/or operation 806.
Operation 802 illustrates adjustment and mates at least one threshold value be associated, with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, with again by the data be associated with suspected advertisement and the coupling of data that is associated with the one or more coherent fragment returned from media content database to obtain one or more possible coupling.Retrieve the initial operation (perhaps by via the operation disclosed by ' 781 patents and/or related application) of mating with using loose coupling tolerance in order to performance object from relative large media content database to be formed and contrast, can by claimed advertisement be completed additional matches compared with the Search Results of relatively small amount, this additional matches is (perhaps again by ' 781 patents and/or the operation disclosed by related application) that use stricter coupling tolerance to complete.Use the coupling of stricter tolerance can be associated with computationally more intensive operation; But when for comparing the fragment of less amount, additional calculations burden is in the acceptable limit.
Further, operation 804 illustrates and this candidate segment is mated with this one or more consecutive frames sequence be stored in before in this data storage based at least one adjusted threshold value at least in part.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, the data be associated with claimed advertisement and the matching operation of data be associated with possible coupling have come by the stricter tolerance set up in operation 802.Operation 802 and 804 can represent that the step 2 that discloses Anywhere at least partially herein.At least in part based on the coupling that tolerance is stricter, one or more in the possible occurrence returned before can be removed from retrieved occurrence.
Further, if operation 806 illustrates at least in part based at least one adjusted threshold value, this candidate segment and this one or more consecutive frames sequences match be stored in before in this data storage, then determine starting point and the end point of this candidate segment.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, again according to before claimed advertisement inspection from any coupling of media content database retrieval.The effect of this additional examination can be identify the commercial advertisement claimed boundary (namely, from claimed commercial advertisement or terminate to reduce any unnecessary frame or to add back from claimed commercial advertisement or end lacks frame, both by carrying out with comparing of the occurrence retrieved from media content database before).Operation 806 can be relevant to the step 3 disclosed Anywhere herein at least in part.
Fig. 8 further illustrates example embodiment, wherein operates 802 and can comprise at least one additional operations.Additional operations can comprise operation 808 and/or operation 810.
Operation 808 illustrates at least one radius adjusting and be associated with a path tracing algorithm, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, can by adjustment with the radius that PPLEB searches for and/or path tracing algorithm is associated, perhaps make tolerance stricter by the operation disclosed in ' 781 patent and/or related application.
Further, operation 810 illustrates adjustment at least one duration relevant to at least one case that a path tracing algorithm is associated, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, can be searched for PPLEB by adjustment and/or path tracing algorithm is associated time major radius, perhaps make tolerance stricter by the operation disclosed in ' 781 patent and/or related application.This duration can such as remove from the time case arranged with time-based discount branch mailbox (timediscountbinning) at token before time quantum relevant.This duration can such as describe the live time be associated with one or more tokens of the time case of time-based discount branch mailbox arrangement.
Fig. 8 further illustrates example embodiment, wherein operates 806 and can comprise at least one additional operations.Additional operations can comprise operation 812, operation 814 and/or operation 816.
Operation 812 illustrates adjustment and mates at least one threshold value be associated, with returning of comparatively high amts, this at least one threshold value adjusted suspects that item is associated.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, adjusted stricter tolerance for the relaxed pine of additional matches in operation 802, because the stricter tolerance coupling by operation 804 removes retrieved occurrence, this additional matches may comprise claimed advertisement and less the mating retrieved from media content database.
Further, the operation 814 one or more instructions illustrated the one or more instruction be associated with each frame in this candidate segment is associated with a respective frame in this one or more consecutive frames sequence be stored in before in this data storage compare, and this is more at least in part based on this adjusted at least one threshold value.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, looser tolerance (such as, ' 781 patent or the radius described in related application, duration, other business etc.) is used again to compare claimed advertisement and residue occurrence.
Further, operation 816 illustrates and relatively tests each frame in this candidate segment based on this at least in part and be stored in the inconsistency between a respective frame in this one or more consecutive frames sequence in this data storage before.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, each point of two samples can determine the boundary of claimed advertisement in this test process at interval farther (such as, perhaps in time or in distance) more accurately wherein.
Fig. 9 illustrates the further alternate embodiment of operation 816, and this operation can comprise at least one additional operations.Operation 816 can comprise operation 902, operation 904, operation 906 and/or operation 908.
If operation 902 illustrates any frame in this candidate segment being stored in before in this one or more consecutive frames sequence in this data storage and do not have a corresponding occurrence, then the frame of corresponding for the neither one in this candidate segment occurrence is removed from this one or more consecutive frames sequence be stored in before this data storage.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, can remove perhaps the beginning of claimed advertisement or end or perhaps the centre of claimed advertisement, the excessive frame that do not have corresponding occurrence in the fragment early retrieved from media content database.
If the operation 904 any frames illustrated in this one or more consecutive frames sequence be stored in before in this data storage do not have a corresponding occurrence in this candidate segment, then add this frame in this one or more consecutive frames sequence be stored in before in this data storage to this candidate segment.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, find in the fragment retrieved from media content database, in claimed advertisement, do not have the frame of corresponding occurrence to may be added to the fragment of the advertisement that expression is claimed, perhaps in the beginning of claimed advertisement or end and/or the centre in claimed advertisement.
Operation 906 is relatively tested each frame in this candidate segment based on this at least in part and is stored in the inconsistency between a respective frame in this one or more consecutive frames sequence in this data storage before.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, the advertisement claimed and comparing for one or more occurrences remained of any inconsistency between it by step 1 and 2 of retrieving from media content database, this can be included in the step 3 disclosed Anywhere herein at least partially.
Operation 908 illustrates any inconsistency remedied and found by test, and this remedies the border that can be used to identification of candidate item.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, the result of operation 906 helps to identify the border of television commercial suspected and does not evaluatedly have missing point (namely, in two samples a little all mate) and the beginning boundary had in the time threshold of the initial commercial advertisement suspected and terminate boundary (namely, if coupling possible be at first 15 seconds long, then the result of loose content search can not be 30 seconds long etc.).
Figure 10 illustrates the alternate embodiment of the example operational flow 500 of Fig. 5.Fig. 6 illustrates example embodiment, wherein operates 502 and can comprise at least one additional operations with operation 506.Additional operations can comprise operation 1002.
Operation 1002 illustrates picked-up at least two audiovisual streams, comprising at least some data that the one or more frames at least one audiovisual streams in major general and this at least two audiovisual streams are associated is stored in a program content data memory, this at least some data comprise to from wherein receive to the audiovisual streams of this one or more frame at least one instruction, and test this candidate segment determined at least one occurrence in a known advertisement data storage, and if test returns at least one occurrence in this known advertisement data storage to this candidate segment, at least some data be then associated to major general with this candidate segment remove from this program content data memory.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, when absorbing, to ground transmission and/or otherwise receive a not only channel and the data be associated with the data flow from channel are stored in media content database, parallel or substantially concurrently to ground transmission with store the data be associated with each channel.Concrete commercial advertisement can be received on any or all channel in a not only channel, thus many examples of the data be associated with the concrete commercial advertisement be stored in media content database may be produced.Presently disclosed with determine that the operation of the data be associated with the advertisement in media content database may be used for identifying and/or process the data be associated with concrete advertisement, and no matter which channel this concrete advertisement plays on and/or when this concrete advertisement plays.
Figure 11 illustrates the alternate embodiment of the example operational flow 500 of Fig. 5.Figure 11 illustrates example embodiment, wherein operates 504 and can comprise at least one additional operations.Additional operations can comprise operation 1102, operation 1104, operation 11011 and/or operation 1108.
Operation 1102 illustrates and confirms that this candidate segment has a Low threshold coupling based at least one duration of a candidate segment at least in part.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, particularly about step 1, if the advertisement claimed (also known as making the advertisement suspected, the commercial advertisement suspected, the television commercial suspected, the television advertising suspected) has at least one item in the frame duration or quantity that other commercial advertisements have, then this fragment can be selected as claimed advertisement as " Low threshold coupling ".This desired target duration can be at least five seconds (because the commercial advertisement being less than five seconds is extremely rare or does not exist) and/or be less than 60 seconds or 120 seconds (because the commercial advertisement being longer than 60 seconds or 120 seconds is also extremely rare or does not exist).This is not conclusive test; But the duration of frame and corresponding quantity are the first instructions, wherein follow-up test is intended to confirm this first instruction (that is, confirming with high threshold).
Further, operation 1104 illustrates and confirms that this candidate segment has a high threshold and mates based on one or more fingerprint of this candidate segment with mating of a known advertisement at least in part.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, the data (again, being perhaps fingerprint) that the data be associated with one or more frames of claimed advertisement (being perhaps fingerprint) are associated with one or more frames of the possible coupling fragment in media content database are compared.These fingerprints and/or relatively can be produced by the operation that discloses in ' 781 patent and/or related application.The result compared data set can be more strong instruction or or even confirm the commercial advertisement claimed and the fragment match (" high threshold mates ") from database.
Further, operate 1106 illustrate determine it can is advertisement, commercial advertisement, public service bulletin, publicity, the time spot at least partially, the fragment of at least one at least partially or in the TV programme publicity being about to present of advertisement pod.Such as, as as shown in Fig. 1 to Fig. 3 and/or about described by it, the associated clip disclosed in instant application can be called as advertisement, commercial advertisement, public service bulletin, publicity, the time spot at least partially, advertisement pod at least partially or to be about in the TV programme publicity that presents one or more.May exist other for purposes of this application and just fragment be expressed as the term of associated clip and all this terms in the scope of the application.
Further, operation 1108 illustrates determines a candidate segment, and this candidate segment comprises at least one or more successive video frames of the audiovisual streams of at least one picked-up from this.Such as, as shown in Fig. 1 to Fig. 3 and/or about described by it, continuous videos frame fragment can be comprised from the candidate segment of the successive frame of data flow picked-up.But, expect that the system and method disclosed Anywhere can relate to other aspects of data flow herein, such as, audio frame, the metadata be associated with the frame of data flow or other this embodiments.
Figure 12 illustrates illustrative computer program product 1200, and this computer program can comprise at least one non-transient computer-readable medium.The instruction 1204 of computer program 1200 is further illustrated in Figure 12.Instruction 1204 illustrates the one or more instructions for absorbing at least one audiovisual streams, comprises at least some data be associated with one or more frames of this audiovisual streams to major general and is stored in a program content data memory; For determining one or more instructions of a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this; And and if for testing one or more instructions that at least one occurrence test of a determined candidate segment in a known advertisement data storage removes from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated to major general with this candidate segment.Such as, as shown in Fig. 1 to Fig. 3 and Fig. 5 to Figure 11 and/or about described by it, computer program can comprise and is coded in one or more instructions that are on one or more non-transient computer-readable medium and/or that stored by it.This one or more instruction causes this one or more treatment facility to perform multi-mode operation when being performed by one or more treatment facility, these operations comprise: absorb at least one audiovisual streams, comprise at least some data be associated with one or more frames of this audiovisual streams to major general and are stored in a program content data memory; Determine a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams from least one picked-up; And test determined candidate segment at least one occurrence in a known advertisement data storage, and if test to return at least one occurrence in this known advertisement data storage to this candidate segment, then remove from this program content data memory at least some data that major general is associated with this candidate segment.Aforementioned operation can be similar to and/or be substantially similar to (but being not limited to) other local corresponding operatings disclosed herein at least partly.
Figure 13 illustrates example system 1300.System 1300 can comprise circuit 1302, circuit 1304 and/or circuit 1306.
Circuit 1302 illustrates the circuit being configured at least one audiovisual streams of picked-up, comprises at least some data be associated with one or more frames of this audiovisual streams to major general and is stored in a program content data memory.Such as, as as shown in Fig. 1 to Fig. 3 and Fig. 5 to Figure 11 and/or about described by it, circuit 1302 can cause and has and be similar at least partly and/or be substantially similar to (be not limited to but) and the operation of the effect of other local corresponding operatings disclosed herein.
Next, circuit 1304 illustrates the circuit being configured for and determining a candidate segment, and this candidate segment comprises at least one or more successive frame of the audiovisual streams from least one picked-up.Such as, as as shown in Fig. 1 to Fig. 3 and Fig. 5 to Figure 11 and/or about described by it, circuit 1304 can cause and has and be similar at least partly and/or be substantially similar to (be not limited to but) and the operation of the effect of other local corresponding operatings disclosed herein.
Next, and if circuit 1306 illustrates the circuit being configured at least one occurrence test of the determined candidate segment of test in a known advertisement data storage and removing from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated with this candidate segment to major general.Such as, as as shown in Fig. 1 to Fig. 3 and Fig. 5 to Figure 11 and/or about described by it, circuit 1306 can cause and has and be similar at least partly and/or be substantially similar to (be not limited to but) and the operation of the effect of other local corresponding operatings disclosed herein.
System and method described in this specification, flow chart and structured flowchart can realize in the computer processing system comprising program code, and this program code comprises the program command that can be performed by computer processing system.Other implementations can also be used.In addition, flow chart described herein and structured flowchart describe the concrete grammar and/or corresponding actions of supporting multiple step and corresponding function (these steps and corresponding function support disclosed by constructional device), and may be used for realizing corresponding software configuration and algorithm and equivalent thereof.
The embodiment of the theme disclosed in this specification may be implemented as one or more computer program, that is, be coded in one or more modules of the computer program instructions on tangible program carrier, operates to be performed by data processing equipment or to control it.Computer storage media can be machine readable storage device, machine-readable storage substrate, memory devices or the one or more combination in them.
Computer program (being also called program, software, software application, script or code) can be write with any type of programming language, comprise compiling type language or interpreted languages or statement type language or program language, and it can be disposed by any form, comprise as free-standing program or other unit of using in a computing environment as module, assembly, subroutine or be suitable for.Computer program not necessarily corresponds to the file in file system.Program can be stored in other programs of maintenance of file or the part of data (such as, be stored in the one or more scripts in marking language document), be stored in be exclusively used in discussed program Single document in or be stored in multiple coordinative file (such as, storing the file of multiple parts of one or more module, subprogram or code).Computer program can be deployed on a computer or be positioned at a website or be distributed in multiple website and by multiple computers of suitable interconnection of telecommunication network are performed.
Process described in this specification or logic flow can be performed by the one or more programmable processors performing one or more computer program and operate to perform inputting data and generate the function exported.These processes or logic flow can also be performed by device, and device can also be implemented as dedicated logic circuit, such as, and FPGA (field programmable gate array) or ASIC (application-specific integrated circuit (ASIC)).
The requisite element of computer is processor for performing instruction and one or more memory devices for storing instruction and data.Usually, computer also will comprise one or more memory device (such as, disk, magneto optical disk or CD) for storing data or operatively be connected into for from wherein receiving data or to its transmission data or not only receive but also transmit data.But computer does not need to have this equipment.The processor being suitable for performing computer program only comprises any one or more processors of the digital computer of general purpose microprocessor and special microprocessor and any kind for example and without limitation.Usually, processor will receive instruction and data from read-only memory or random access memory or both.
In order to provide with the user of system described herein or manager mutual, the embodiment of the theme described in this specification can be implemented in be had for showing the display device of information (such as to user, CRT (cathode ray tube) or LCD (liquid crystal display) watch-dog) and user can be provided on the keyboard (such as, mouse or trackball) of input and the computer of pointing device to computer by it.The equipment of other kinds also may be used for providing and user interactions.Such as, the feedback being supplied to user can be any type of sensory feedback, such as, and visual feedback, audio feedback or tactile feedback; And with the input of any form reception from user, sound, voice or sense of touch input can be comprised.
The embodiment of the theme described in this specification can be implemented in computing system, and this computing system comprises the aft-end assembly of one or more data server or comprises having one or more middleware component (as application server) or comprising and have the front end assemblies (as client computer) of graphic user interface or Web browser (user or keeper can be mutual by some implementation of itself and the theme described in this specification) or the combination in any of one or more this aft-end assembly, middleware or front end assemblies.The assembly of system can by any digital data communications form or medium (as communication network) interconnection.Computing system can comprise client and server.Client and server usually away from each other and usually mutual by communication network.The relation of client and server by means of run on respective computer and the computer program each other with client server relationship produce.
Although this specification comprises many specific implementation mode details, these should not be interpreted as the restriction of the scope to the things that any invention maybe may require, but are interpreted as may specific to the description of the feature of the specific embodiment of concrete invention.Some feature described in this manual under the background of independent embodiment can also realize in single embodiment by combining form.
On the contrary, the different characteristic described under the background of single embodiment also can by independent or realize in many embodiment: in the mode of any suitable sub-portfolio.And, although more than feature can be described to some combinations and even so be required at first, but in some cases can be in vitro with combination from one or more features of required combination, and required combination can for the change of sub-portfolio or sub-portfolio.
Similarly, although depict operation with concrete order in accompanying drawing, this should not be understood as that and require that this operation is with shown concrete order or with order execution in order, or the operation of all displayings can be performed, to realize the result of making us wishing.In some cases, multitask process and parallel processing may be favourable.And, the separation of the different system assembly in above-described embodiment should not be understood as that and all require this separation in all embodiments, and it should be understood that described program element and system usually can be integrated together in single software product or encapsulate in multiple software product.
That write present description illustrates optimal mode of the present invention and provides multiple example to describe the present invention and those of ordinary skill in the art can be made to make and use the present invention.This specification of writing does not limit the invention to set forth precise terms.Therefore, although describe the present invention in detail with reference to the above example set forth, those of ordinary skill in the art can implement change, amendment to these examples and change and do not depart from the scope of the present invention.

Claims (20)

1. a method, comprising:
Absorb at least one audiovisual streams, comprise at least some data be associated with one or more frames of this audiovisual streams to major general and be stored in a program content data memory;
Determine a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this; And
Test this candidate segment determined at least one occurrence in a known advertisement data storage, and if test to return at least one occurrence in this known advertisement data storage to this candidate segment, then remove from this program content data memory at least some data that major general is associated with this candidate segment.
2. the method for claim 1, comprises further:
Test this candidate segment determined at least one occurrence in this program content data memory, and if test returns at least one occurrence in this program content data memory to this candidate segment, then at least some data be associated to major general with this candidate segment remove and at least some data be associated with this candidate segment are stored in this known advertisement data storage from this program content data memory.
3. the method for claim 1, wherein determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) comprising:
Receive the one or more instructions to a frame of this absorbed stream of audiovisual data; Analyze this one or more instruction to a frame, comprise and at least determine this one or morely indicates whether it may is a start frame of a candidate segment;
If determine a start frame, then whether analyze the one or more frames received after this start frame, comprising one of this one or more frame at least determining to receive after this start frame may be an end frame; And
If determine an end frame, then set up this one or more frame and (iii) this end frame that (i) this start frame, (ii) receive after this start frame and before this end frame as this candidate segment.
4. method as claimed in claim 3, wherein, analyze this one or more instruction to a frame (comprise at least determine these one or more indicate whether it may is a start frame of a candidate segment) and analyze the one or more frames (comprising whether the frame at least determining to receive after this start frame may be an end frame) received after this start frame and comprising:
Determine at least one item whether a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, and if at least one item that a frame is a monochrome frame or has in a frame of one or more fingerprint value substantially different from and then previous frame, then set up this frame as at least one item in a start frame or an end frame.
5. the method for claim 1, wherein determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) comprising:
Receive the one or more instructions to a frame of this absorbed stream of audiovisual data; The data be associated with the frame end received recently coherent picked-up frame sequence and the data be associated with the one or more consecutive frames sequences be stored in before in this program content data memory are compared; And
The one or more instructions to the one or more consecutive frames sequences be stored in before in this program content data memory are provided at least in part based on this comparing data.
6. method as claimed in claim 5, comprises further:
For each frame sequence in this indicated one or more consecutive frames sequence, determine whether this consecutive frames sequence is an advertisement.
7. method as claimed in claim 6, wherein, determine whether this consecutive frames row are that an advertisement comprises:
At least one item in number of seconds length or the frame count that is associated with this consecutive frames sequence is assessed, and if number of seconds length or frame count are substantially similar to a standard advertisement length, then sets up this consecutive frames sequence as a candidate segment.
8. method as claimed in claim 7, comprises further:
Adjust and mate at least one threshold value be associated, with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated;
Based on this adjusted at least one threshold value, this candidate segment is mated with this one or more consecutive frames sequence be stored in before in this data storage at least in part; And
If at least in part based on this adjusted this candidate segment of at least one threshold value and this one or more consecutive frames sequences match be stored in before in this data storage, then determine starting point and the end point of this candidate segment.
9. method as claimed in claim 8, wherein, adjust at least one threshold value (with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated) be associated with coupling to comprise: adjust at least one radius be associated with a path tracing algorithm, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.
10. method as claimed in claim 8, wherein, adjusts at least one threshold value (with returning of lower quantity, this at least one threshold value adjusted suspects that item is associated) be associated with coupling and comprising:
Adjust at least one duration relevant to at least one case that a path tracing algorithm is associated, with returning of lower quantity, this at least one radius adjusted suspects that item is associated.
11. methods as claimed in claim 8, wherein, determine that the starting point of this candidate segment and end point comprise:
Adjust and mate at least one threshold value be associated, with returning of comparatively high amts, this at least one threshold value adjusted suspects that item is associated;
One or more instructions that the one or more instruction be associated with each frame in this candidate segment is associated with a respective frame in this one or more consecutive frames sequence be stored in before in this data storage compared, this is more at least in part based on this adjusted at least one threshold value; And
Relatively test each frame in this candidate segment based on this at least in part and be stored in the inconsistency between a respective frame in this one or more consecutive frames sequence in this data storage before.
12. methods as claimed in claim 11, wherein, each frame in this candidate segment is relatively tested based on this at least in part and the inconsistency be stored in before between a respective frame in this one or more consecutive frames sequence in this data storage comprises:
If any frame in this candidate segment does not have a corresponding occurrence being stored in before in this one or more consecutive frames sequence in this data storage, then the frame of corresponding for the neither one in this candidate segment occurrence is removed from this one or more consecutive frames sequence be stored in before this data storage.
13. methods as claimed in claim 11, wherein, each frame in this candidate segment is relatively tested based on this at least in part and the inconsistency be stored in before between a respective frame in this one or more consecutive frames sequence in this data storage comprises:
If any frame be stored in this one or more consecutive frames sequence in this data storage does not have a corresponding occurrence in this candidate segment before, then add this frame in this one or more consecutive frames sequence be stored in before in this data storage to this candidate segment.
14. methods as claimed in claim 11, wherein, each frame in this candidate segment is relatively tested based on this at least in part and the inconsistency be stored in before between a respective frame in this one or more consecutive frames sequence in this data storage comprises:
Relatively test each frame in this candidate segment based on this at least in part and be stored in the inconsistency between a respective frame in this one or more consecutive frames sequence in this data storage before; And
Remedy any inconsistency found by test, this remedies the border that can be used to identification of candidate item.
15. the method for claim 1, wherein, absorb at least one audiovisual streams (comprising at least some data be associated with one or more frames of this audiovisual streams to major general to be stored in a program content data memory) and and if test this candidate segment determined at least one occurrence in a known advertisement data storage and test this candidate segment and return at least some data that at least one occurrence in this known advertisement data storage is then associated with this candidate segment to major general and remove from this program content data memory and comprise:
Absorb at least two audiovisual streams, comprising at least some data that the one or more frames at least one audiovisual streams in major general and this at least two audiovisual streams are associated is stored in a program content data memory, this at least some data comprise to from wherein receive to the audiovisual streams of this one or more frame at least one instruction, and test this candidate segment determined at least one occurrence in a known advertisement data storage, and if test returns at least one occurrence in this known advertisement data storage to this candidate segment, any one in this at least one occurrence and this at least two audiovisual streams is relevant, at least some data be then associated to major general with this candidate segment remove from this program content data memory.
The method of claim 1, wherein 16. determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) comprising:
At least one duration at least in part based on a candidate segment confirms that this candidate segment has a Low threshold coupling; And
With mating of a known advertisement, one or more fingerprint at least in part based on this candidate segment confirms that this candidate segment has a high threshold and mates.
The method of claim 1, wherein 17. determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) comprising:
Determine it can is advertisement, commercial advertisement, public service bulletin, publicity, the time spot at least partially, the fragment of at least one at least partially or in the TV programme publicity being about to present of advertisement pod.
The method of claim 1, wherein 18. determine that a candidate segment (this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this) comprising:
Determine a candidate segment, this candidate segment comprises at least one or more successive video frames of the audiovisual streams of at least one picked-up from this.
19. 1 kinds of computer programs, comprising:
At least one non-transient computer-readable medium, this medium comprises at least:
For absorbing one or more instructions of at least one audiovisual streams, comprising at least some data be associated with one or more frames of this audiovisual streams to major general and being stored in a program content data memory;
For determining one or more instructions of a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams of at least one picked-up from this; And
And if for testing one or more instructions that at least one occurrence test of a determined candidate segment in a known advertisement data storage removes from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated to major general with this candidate segment.
20. 1 kinds of systems, comprising:
Be configured for the circuit of at least one audiovisual streams of picked-up, comprise at least some data be associated with one or more frames of this audiovisual streams to major general and be stored in a program content data memory;
Be configured for the circuit determining a candidate segment, this candidate segment comprises at least one or more successive frame of the audiovisual streams from least one picked-up; And
And if be configured for the circuit that at least one occurrence test of the determined candidate segment of test in a known advertisement data storage removes from this program content data memory at least some data that at least one occurrence that this candidate segment returns in this known advertisement data storage is then associated to major general with this candidate segment.
CN201480015936.XA 2013-03-15 2014-03-17 The system and method for real-time television purposes of commercial detection Active CN105052161B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811471681.4A CN109905726B (en) 2013-03-15 2014-03-17 System and method for real-time television advertisement detection

Applications Claiming Priority (19)

Application Number Priority Date Filing Date Title
US201361791578P 2013-03-15 2013-03-15
US61/791,578 2013-03-15
US14/089,003 US8898714B2 (en) 2009-05-29 2013-11-25 Methods for identifying video segments and displaying contextually targeted content on a connected television
US14/089,003 2013-11-25
PCT/US2014/030795 WO2014145938A1 (en) 2013-03-15 2014-03-17 Systems and methods for real-time television ad detection using an automated content recognition database
US14/217,075 US9055309B2 (en) 2009-05-29 2014-03-17 Systems and methods for identifying video segments for displaying contextually relevant content
US14/217,075 2014-03-17
USPCT/US2014/30805 2014-03-17
US14/217,039 2014-03-17
US14/217,435 2014-03-17
US14/217,039 US9055335B2 (en) 2009-05-29 2014-03-17 Systems and methods for addressing a media database using distance associative hashing
PCT/US2014/030782 WO2014145929A1 (en) 2013-03-15 2014-03-17 Systems and methods for addressing a media database using distance associative hashing
US14/217,435 US9094715B2 (en) 2009-05-29 2014-03-17 Systems and methods for multi-broadcast differentiation
US14/217,425 US9071868B2 (en) 2009-05-29 2014-03-17 Systems and methods for improving server and client performance in fingerprint ACR systems
US14/217,375 US9094714B2 (en) 2009-05-29 2014-03-17 Systems and methods for on-screen graphics detection
US14/217,375 2014-03-17
USPCT/US2014/30782 2014-03-17
US14/217,425 2014-03-17
PCT/US2014/030805 WO2014145947A1 (en) 2013-03-15 2014-03-17 Systems and methods for identifying video segments for displaying contextually relevant content

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN201811471681.4A Division CN109905726B (en) 2013-03-15 2014-03-17 System and method for real-time television advertisement detection

Publications (2)

Publication Number Publication Date
CN105052161A true CN105052161A (en) 2015-11-11
CN105052161B CN105052161B (en) 2018-12-28

Family

ID=54261403

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480015936.XA Active CN105052161B (en) 2013-03-15 2014-03-17 The system and method for real-time television purposes of commercial detection

Country Status (7)

Country Link
CN (1) CN105052161B (en)
BR (1) BR112015023380B1 (en)
CA (1) CA2906192C (en)
CL (1) CL2015002619A1 (en)
HK (1) HK1218193A1 (en)
MX (2) MX366327B (en)
WO (1) WO2014145938A1 (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975924A (en) * 2016-04-29 2016-09-28 杭州当虹科技有限公司 Regression testing method for precisely recognizing ad content based on video frame statistics
CN106507141A (en) * 2016-10-19 2017-03-15 天脉聚源（北京）科技有限公司 A kind of channel broadcast content monitoring method and device
CN107613326A (en) * 2017-09-30 2018-01-19 深圳市鑫汇达机械设计有限公司 One kind identifies accurate television advertising identifying system
CN107633848A (en) * 2016-07-19 2018-01-26 阿基米德（上海）传媒有限公司 It is a kind of to remove the method for advertisement by identifying audio-frequency fingerprint
CN108959187A (en) * 2018-04-09 2018-12-07 中国平安人寿保险股份有限公司 A kind of variable branch mailbox method, apparatus, terminal device and storage medium
CN109522531A (en) * 2017-09-18 2019-03-26 腾讯科技（北京）有限公司 Official documents and correspondence generation method and device, storage medium and electronic device
CN110537371A (en) * 2017-06-30 2019-12-03 尼尔森（美国）有限公司 Frame certainty for automatation content identification
CN111077326A (en) * 2019-12-20 2020-04-28 中译语通文娱科技(青岛)有限公司 Detection technology based on AI technology pre-perception capability
CN112948636A (en) * 2021-03-24 2021-06-11 黑龙江省能嘉教育科技有限公司 Regional education cloud resource sharing system and method
CN114979691A (en) * 2022-05-23 2022-08-30 上海影谱科技有限公司 Statistical analysis method and system for sports event rebroadcasting equity advertisement

Families Citing this family (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10631068B2 (en) 2008-11-26 2020-04-21 Free Stream Media Corp. Content exposure attribution based on renderings of related content across multiple devices
US9961388B2 (en) 2008-11-26 2018-05-01 David Harrison Exposure of public internet protocol addresses in an advertising exchange server to improve relevancy of advertisements
US8180891B1 (en) 2008-11-26 2012-05-15 Free Stream Media Corp. Discovery, access control, and communication with networked services from within a security sandbox
US9986279B2 (en) 2008-11-26 2018-05-29 Free Stream Media Corp. Discovery, access control, and communication with networked services
US9026668B2 (en) 2012-05-26 2015-05-05 Free Stream Media Corp. Real-time and retargeted advertising on multiple screens of a user watching television
US10419541B2 (en) 2008-11-26 2019-09-17 Free Stream Media Corp. Remotely control devices over a network without authentication or registration
US10567823B2 (en) 2008-11-26 2020-02-18 Free Stream Media Corp. Relevant advertisement generation based on a user operating a client device communicatively coupled with a networked media device
US10977693B2 (en) 2008-11-26 2021-04-13 Free Stream Media Corp. Association of content identifier of audio-visual data with additional data through capture infrastructure
US9519772B2 (en) 2008-11-26 2016-12-13 Free Stream Media Corp. Relevancy improvement through targeting of information based on data gathered from a networked device associated with a security sandbox of a client device
US9154942B2 (en) 2008-11-26 2015-10-06 Free Stream Media Corp. Zero configuration communication between a browser and a networked media device
US10334324B2 (en) 2008-11-26 2019-06-25 Free Stream Media Corp. Relevant advertisement generation based on a user operating a client device communicatively coupled with a networked media device
US10880340B2 (en) 2008-11-26 2020-12-29 Free Stream Media Corp. Relevancy improvement through targeting of information based on data gathered from a networked device associated with a security sandbox of a client device
US9386356B2 (en) 2008-11-26 2016-07-05 Free Stream Media Corp. Targeting with television audience data across multiple screens
WO2016172363A1 (en) * 2015-04-24 2016-10-27 Cyber Resonance Corporation Methods and systems for performing signal analysis to identify content types

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060029368A1 (en) * 1999-11-18 2006-02-09 Vulcan Patents, Llc Iterative, maximally probable, batch-mode commercial detection for audiovisual content
US20060245724A1 (en) * 2005-04-29 2006-11-02 Samsung Electronics Co., Ltd. Apparatus and method of detecting advertisement from moving-picture and computer-readable recording medium storing computer program to perform the method
WO2007114796A1 (en) * 2006-04-05 2007-10-11 Agency For Science, Technology And Research Apparatus and method for analysing a video broadcast
WO2009150425A3 (en) * 2008-06-10 2010-09-10 Half Minute Media Ltd Automatic detection of repeating video sequences
CN102523482A (en) * 2011-12-07 2012-06-27 中山大学 Advertisement monitoring technology based on video content and regression method
CN102760169A (en) * 2012-06-13 2012-10-31 天脉聚源(北京)传媒科技有限公司 Method for detecting advertising slots in television direct transmission streams

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4321518B2 (en) * 2005-12-27 2009-08-26 三菱電機株式会社 Music section detection method and apparatus, and data recording method and apparatus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060029368A1 (en) * 1999-11-18 2006-02-09 Vulcan Patents, Llc Iterative, maximally probable, batch-mode commercial detection for audiovisual content
US20060245724A1 (en) * 2005-04-29 2006-11-02 Samsung Electronics Co., Ltd. Apparatus and method of detecting advertisement from moving-picture and computer-readable recording medium storing computer program to perform the method
WO2007114796A1 (en) * 2006-04-05 2007-10-11 Agency For Science, Technology And Research Apparatus and method for analysing a video broadcast
WO2009150425A3 (en) * 2008-06-10 2010-09-10 Half Minute Media Ltd Automatic detection of repeating video sequences
CN102523482A (en) * 2011-12-07 2012-06-27 中山大学 Advertisement monitoring technology based on video content and regression method
CN102760169A (en) * 2012-06-13 2012-10-31 天脉聚源(北京)传媒科技有限公司 Method for detecting advertising slots in television direct transmission streams

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975924A (en) * 2016-04-29 2016-09-28 杭州当虹科技有限公司 Regression testing method for precisely recognizing ad content based on video frame statistics
CN107633848A (en) * 2016-07-19 2018-01-26 阿基米德（上海）传媒有限公司 It is a kind of to remove the method for advertisement by identifying audio-frequency fingerprint
CN106507141A (en) * 2016-10-19 2017-03-15 天脉聚源（北京）科技有限公司 A kind of channel broadcast content monitoring method and device
CN110537371A (en) * 2017-06-30 2019-12-03 尼尔森（美国）有限公司 Frame certainty for automatation content identification
CN109522531A (en) * 2017-09-18 2019-03-26 腾讯科技（北京）有限公司 Official documents and correspondence generation method and device, storage medium and electronic device
CN109522531B (en) * 2017-09-18 2023-04-07 腾讯科技（北京）有限公司 Document generation method and device, storage medium and electronic device
CN107613326A (en) * 2017-09-30 2018-01-19 深圳市鑫汇达机械设计有限公司 One kind identifies accurate television advertising identifying system
CN108959187A (en) * 2018-04-09 2018-12-07 中国平安人寿保险股份有限公司 A kind of variable branch mailbox method, apparatus, terminal device and storage medium
CN108959187B (en) * 2018-04-09 2023-09-05 中国平安人寿保险股份有限公司 Variable box separation method and device, terminal equipment and storage medium
CN111077326A (en) * 2019-12-20 2020-04-28 中译语通文娱科技(青岛)有限公司 Detection technology based on AI technology pre-perception capability
CN112948636A (en) * 2021-03-24 2021-06-11 黑龙江省能嘉教育科技有限公司 Regional education cloud resource sharing system and method
CN112948636B (en) * 2021-03-24 2022-09-27 黑龙江省能嘉教育科技有限公司 Regional education cloud resource sharing system and method
CN114979691A (en) * 2022-05-23 2022-08-30 上海影谱科技有限公司 Statistical analysis method and system for sports event rebroadcasting equity advertisement
CN114979691B (en) * 2022-05-23 2023-07-28 上海影谱科技有限公司 Statistical analysis method and system for advertisement of retransmission rights of sports event

Also Published As

Publication number Publication date
MX366327B (en) 2019-07-05
CL2015002619A1 (en) 2016-04-15
HK1218193A1 (en) 2017-02-03
CN105052161B (en) 2018-12-28
CA2906192C (en) 2020-10-27
MX2015012511A (en) 2016-01-12
BR112015023380B1 (en) 2023-03-28
WO2014145938A1 (en) 2014-09-18
BR112015023380A8 (en) 2018-08-14
BR112015023380A2 (en) 2017-07-18
MX2019008020A (en) 2019-09-04
CA2906192A1 (en) 2014-09-18

Similar Documents

Publication Publication Date Title
CN105052161A (en) Systems and methods for real-time television ad detection using an automated content recognition database
US8930980B2 (en) Systems and methods for real-time television ad detection using an automated content recognition database
US9602855B2 (en) Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements
US10237612B2 (en) Identification and presentation of internet-accessible content associated with currently playing television programs
US8424052B2 (en) Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements
AU2016291674B2 (en) Systems and methods for partitioning search indexes for improved efficiency in identifying media segments
US9094715B2 (en) Systems and methods for multi-broadcast differentiation
EP2982131B1 (en) Systems and methods for real-time television ad detection using an automated content recognition database
EP2541963B1 (en) Method for identifying video segments and displaying contextually targeted content on a connected television
US9553922B1 (en) Media event based social networking interfaces
US10455269B2 (en) Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements
US20240031269A1 (en) Fusing online media monitoring data with secondary online data feeds to generate ratings data for online media exposure
US20230336837A1 (en) Detection of common media segments
US10116982B2 (en) Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements
US11991405B2 (en) Systems and methods for automated extraction of closed captions in real time or near real-time and tagging of streaming data for advertisements
CN105451068A (en) Electronic program list generation method and device
US20230283821A1 (en) Data translation for video-viewing activity
Chuang et al. Use second screen to enhance TV viewing experiences

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C41 Transfer of patent application or patent right or utility model
TA01 Transfer of patent application right

Effective date of registration: 20160901

Address after: Delaware

Applicant after: Granville Construction Technology Co., Ltd.

Address before: American California

Applicant before: NEUMEIER ZEEV

REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 1218193

Country of ref document: HK

CB02 Change of applicant information
CB02 Change of applicant information

Address after: Delaware

Applicant after: Structural data Co Ltd

Address before: Delaware

Applicant before: Granville Construction Technology Co., Ltd.

GR01 Patent grant
GR01 Patent grant