WO2014145938A1 - Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenu automatisée - Google Patents

Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenu automatisée Download PDF

Info

Publication number
WO2014145938A1
WO2014145938A1 PCT/US2014/030795 US2014030795W WO2014145938A1 WO 2014145938 A1 WO2014145938 A1 WO 2014145938A1 US 2014030795 W US2014030795 W US 2014030795W WO 2014145938 A1 WO2014145938 A1 WO 2014145938A1
Authority
WO
WIPO (PCT)
Prior art keywords
candidate segment
frame
frames
data store
match
Prior art date
Application number
PCT/US2014/030795
Other languages
English (en)
Inventor
Zeev Neumeier
Brian Reed
Original Assignee
Zeev Neumeier
Brian Reed
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
Priority to CA2906199A priority Critical patent/CA2906199C/fr
Priority claimed from PCT/US2014/030805 external-priority patent/WO2014145947A1/fr
Priority to BR112015023369-4A priority patent/BR112015023369B1/pt
Priority to MX2020001441A priority patent/MX2020001441A/es
Priority to CN201811395356.4A priority patent/CN110083739B/zh
Priority to CA3173549A priority patent/CA3173549A1/fr
Priority to CA2906173A priority patent/CA2906173C/fr
Priority to PCT/US2014/030782 priority patent/WO2014145929A1/fr
Priority to MX2015012512A priority patent/MX365827B/es
Priority to BR112015023389-9A priority patent/BR112015023389B1/pt
Priority to CA2906192A priority patent/CA2906192C/fr
Priority to BR112015023380-5A priority patent/BR112015023380B1/pt
Priority claimed from PCT/US2014/030782 external-priority patent/WO2014145929A1/fr
Priority to MX2015012510A priority patent/MX356884B/es
Priority to PCT/US2014/030805 priority patent/WO2014145947A1/fr
Priority to EP14763506.4A priority patent/EP2982131B1/fr
Priority to EP19166400.2A priority patent/EP3534615B1/fr
Priority to CN201480017043.9A priority patent/CN105144141B/zh
Priority to MX2015012511A priority patent/MX366327B/es
Priority claimed from US14/217,039 external-priority patent/US9055335B2/en
Application filed by Zeev Neumeier, Brian Reed filed Critical Zeev Neumeier
Priority to CN201480015936.XA priority patent/CN105052161B/zh
Publication of WO2014145938A1 publication Critical patent/WO2014145938A1/fr
Priority to MX2019007031A priority patent/MX2019007031A/es
Priority to CL2015002621A priority patent/CL2015002621A1/es
Priority to CL2015002623A priority patent/CL2015002623A1/es
Priority to HK16105168.7A priority patent/HK1218193A1/zh
Priority to HK16105782.3A priority patent/HK1217794A1/zh

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

Definitions

  • This invention generally relates to image recognition, and more particularly, to systems and methods for real-time television ad detection using an automated content recognition database.
  • an exemplary method related to real-time television ad detection using an automated content recognition database may include ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream; and testing the determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • an exemplary method related to real-time television ad detection using an automated content recognition database may further include testing the determined candidate segment for at least one match in the data store of program content and, if testing the candidate segment returns at least one match in the data store of program content, at least removing at least some data associated with the candidate segment from the data store of program content and storing at least some data associated with the candidate segment in the data store of known advertisements.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may include receiving one or more indications of a frame of the ingested audiovisual data stream; analyzing the one or more indications of a frame, including at least determining whether the one or more indications could be a starting frame of a candidate segment; if a starting frame is determined, analyzing one or more frames received subsequent to the starting frame, including at least determining whether one of the one or more frames received subsequent to the starting frame could be an ending frame; and if an ending frame is determined, establishing (i) the starting frame, (ii) the one or more frames received subsequent to the starting frame and previous to the ending frame, and (iii) the ending frame as the candidate segment.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may include receiving one or more indications of a frame of the ingested audiovisual data stream; comparing data associated with a contiguous sequence of ingested frames ending with the most recently received frame with data associated with one or more contiguous sequences of frames previously stored in the data store of program content; and providing one or more indications of one or more contiguous sequences of frames previously stored in the data store of program content based at least partially on the comparing data.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may further include for each of the one or more indicated contiguous sequences of frames, determining whether the contiguous sequence of frames is an advertisement.
  • determining whether the contiguous sequence of frames is an advertisement may include evaluating at least one of a length in seconds or a count in frames associated with the contiguous sequence of frames and, if the at least one of a length in seconds or a count in frames is substantially similar to a standard advertisement length, establishing the contiguous sequence of frames as a candidate segment.
  • evaluating at least one of a length in seconds or a count in frames associated with the contiguous sequence of frames and, if the at least one of a length in seconds or a count in frames is substantially similar to a standard advertisement length, establishing the contiguous sequence of frames as a candidate segment may further include adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a lower returned number of suspects; matching the candidate segment with the one or more contiguous sequences of frames previously stored in the data store based at least partially on the adjusted at least one threshold; and if the candidate segment matches the one or more contiguous sequences of frames previously stored in the data store based at least partially on the adjusted at least one threshold, determining starting and ending points of the candidate segment.
  • adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a lower returned number of suspects may include adjusting at least one radius associated with a path pursuit algorithm, the adjusted at least one radius associated with a lower returned number of suspects.
  • adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a lower returned number of suspects may include adjusting at least one duration related to at least one bin associated with a path pursuit algorithm, the adjusted at least one radius associated with a lower returned number of suspects.
  • determining starting and ending points of the candidate segment may include adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a higher returned number of suspects; comparing one or more indications associated with each frame in the candidate segment with one or more indications associated with a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, the comparing based at least partially on the adjusted at least one threshold; and testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing.
  • testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing may include if any frame of the candidate segment does not have a corresponding match in the one or more contiguous sequences of frames previously stored in the data store, dropping the frame of the candidate segment without a corresponding match from the one or more contiguous sequences of frames previously stored in the data store.
  • testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing may include if any frame of the one or more contiguous sequences of frames previously stored in the data store does not have a corresponding match in the candidate segment, adding the frame of the one or more contiguous sequences of frames previously stored in the data store to the candidate segment.
  • testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing may include testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing; and remediating any inconsistencies found via testing, the remediating operable to identify borders of the candidates.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may include confirming a candidate segment having a low threshold match at least partially based on at least one duration of the candidate segment; and confirming the candidate segment having a high threshold match at least partially based on a match of one or more fingerprints of the candidate segment with a known advertisement.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may include determining a segment which may be at least one of an advertisement, a commercial, a public service announcement, a promotion, at least a portion of an ad break, at least a portion of an ad pod, or an upcoming television programming promotion.
  • determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream may include determining a candidate segment, the candidate segment including at least one or more sequential video frames from the at least one ingested audiovisual stream.
  • an exemplary computer program product related to real-time television ad detection using an automated content recognition database may include at least one non-transitory computer-readable medium, and the at least one non-transitory computer-readable medium may include one or more instructions for ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; one or more instructions for determining a candidate segment, the candidate segment including at least one or more sequential frames from at least one ingested audiovisual stream; and one or more instructions for testing a determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • an exemplary system related to real-time television ad detection using an automated content recognition database may include circuitry configured for ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; circuitry configured for determining a candidate segment, the candidate segment including at least one or more sequential frames from at least one ingested audiovisual stream; and circuitry configured for testing a determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • Figure 1 illustrates a typical advertising break (or ad pod) on a time scale highlighting how commercial messages may be spotted.
  • Commercials may be initially detected if their duration falls within certain parameters (104 Low Threshold) and then confirmed with high confidence if the suspect segment matches a certain existing commercial's finger prints in the database 135.
  • Figure 2 illustrates how the various components of the system interact enabling separate databases of television programing and commercial messages to be built, maintained, and utilized in a manner that enables the reliable real time identification of advertising messages.
  • Figure 3 illustrates a flow chart summarizing the order of the individual steps of the method and how they interrelate.
  • Figure 4 illustrates a prior art flow diagram
  • Figure 5 illustrates an operational flow representing example operations related to real-time television ad detection using an automated content recognition database.
  • Figure 6 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 7 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 8 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 9 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 10 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 11 illustrates an alternative embodiment of the operational flow of Figure 5.
  • Figure 12 illustrates an exemplary computer program product.
  • Figure 13 illustrates a system related to real-time television ad detection using an automated content recognition database.
  • 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.
  • the incoming video is tested against the separate TV ad database. If a match is found in the TV ad database, the video segment is removed from the master TV content database.
  • Such an efficient approach enables the system to remove the highly redundant material of TV ads which are known to repeat often and across many channels. This process of detecting and removing TV ads from the main TV content database reduces the number of false positive matches of the primary television content and improves system performance of a video matching system.
  • the present invention relates generally to video signal processing, and more particularly to techniques for processing multiple streams of broadcast video signals to identify, extract and analyze commercials or other specific types of video content that share certain characteristics or have signatures that match known content.
  • the system to implement said method is composed of a series of software processes running on computer servers.
  • Such servers comprising a microprocessor, data base, input device and output device wherein said data base comprises computer readable instructions stored in fixed memory or other digital storage system and executable by said microprocessor.
  • FIG. 1 illustrates a typical television program channel 106 with an advertisement break 109, known in the television industry as an "ad pod," which typically contains many segments of different lengths of: television ads, public service announcements, and upcoming programming promotions, among other material.
  • a typical television ad 107 is 30 seconds in duration.
  • a typical television programming promotion is 15 seconds in duration.
  • the total length of the ad pod 139 typically varies from 60 seconds to three minutes in total duration.
  • Ad pods and other non-program material occupy more than 33% of an average television programming hour.
  • This large quantity of repeating content can cause an ACR system to generate a considerable number of false positive matches or conversely to find no match at all. In one case, this is because of the repetition of a commercial in the course of the same television programming as well as the repetition of a particular commercial in many different television programs on many different television channels.
  • an unknown video source contains television commercial fingerprints (cues)
  • a database with a high percentage of television commercials will result in many matches throughout the database proportional to the percentage of repetition of said commercial yielding unusable results for the duration of a repeated commercial.
  • this invention introduces an algorithm that detects commercials and other frequently repeating segments of video, such as upcoming programming promos.
  • the basic premise of this algorithm is that commercials are short in duration, repeat many times on a given television channel and repeat across multiple television channels.
  • the television advertisement detection process works as follows: As seen in Figure 2, television program feeds are uploaded processed and output via 202 into the primary matching system database 204 and also sent to the television commercial video detector 203. For each television channel monitored by the invention, there is an instance of the television commercial detector of the invention.
  • the television commercial detector runs a content search process on the incoming feed typically located with the central server means of the invention. This is similar to the process of the invention operating in a connected TV in a user's home where said invention reads pixel patches from one or more screen locations at a prescribed number of samples per time interval. As with the home application, said process further performs numerical processing on said pixel patches to prepare said patches for input to a content matching system which will attempt to match said pixel arrays to a database of known content.
  • the commercial detector content search process continues to search for every possibility match until a matching threshold is reached and the process for that match set ceases. This is different from regular content search in that typically a content search that returns multiple matches is considered to be invalid, because fixed length segments typically do not repeat within the body of a television program.
  • This advertisement search process runs continuously and examines the video from every television program source that is fed to the system of the invention. [0045] For each possible match returned from the above process, the following process is triggered asynchronously allowing the above mentioned algorithm to continue searching while the following process executes in three steps:
  • Step 1 Each possible match is evaluated for length which should be larger than a given threshold, for example, 5 seconds, and smaller then another, perhaps 60 seconds. In Figure 1, this is both a duration, as illustrated in 109, and a low threshold match 101. In practice, this is simply the difference between the timestamp of the first matching point and the last matching point for segments about the predetermined threshold 104 as per the method as disclosed in US Patent 8,585,781.
  • Step 2 If the possible match is within the acceptable parameters of the previous test (step 1) it is then run through the content search again but with more refined test requirements where the same search is performed as previously but requiring the points (fingerprints) of the two samples to match more closely as in 105. The results of this test are evaluated and if the percentages of points (fingerprints) that match this stricter search are less than a given threshold, the possible match is discarded.
  • Step 3 If the possible match passes the previous test it is then run through yet another content search but with much looser configuration, i.e. the same search as before but allowing each point of the two samples to be farther apart, perhaps in at least one of time or distance.
  • the results of this test help identify the borders of the suspected television commercial and are evaluated to have no missing points (i.e. all points in the two samples match) and to have beginning and end boundaries that are within a time threshold of the originally suspected commercial (i.e. if the original possible match was 15 seconds long then the results of the loose content search can't be 30 seconds long, etc.)
  • an unknown video segment sample passes all three tests above then it is assumed to be a television commercial, promotion or public service announcement and information defining said video segment is sent via 206 to the video segment processor 207. If said sample has matched against a television commercial, promotion or public service announcement already in the ad database 205, then the new instance is removed from the primary television program database 204 by the video segment processor 207 and there is no need to place said matched advertisement again in the ad database.
  • FIG. 3 A flow chart summarizing the method is presented in Figure 3.
  • Each television video stream or "channel" is accepted by system 301 and initially tested against an existing database of known commercials, 303. If there is a match, 304, it is removed from the database of TV programming, 308. If there is not a match, it is tested, 307, against the database of known TV programs 308. If it is a match, the video segment matching it is removed from the TV program database, 310 and added to the TV commercial database 311. If it is not a match, then it is assumed to not be a segment of interest 312, and is ignored.
  • Figure 4 illustrates a prior art flow diagram for comparison.
  • Figure 5 illustrates an operational flow 500 representing example operations related to real-time television ad detection using an automated content recognition database.
  • discussion and explanation may be provided with respect to the above-described examples of Figures 1 through 3, and/or with respect to other examples and contexts.
  • the operational flows may be executed in a number of other environments and contexts, and/or in modified versions of Figures 1 through 3.
  • the various operational flows are presented in the sequence(s) illustrated, it should be understood that the various operations may be performed in other orders than those which are illustrated, or may be performed concurrently.
  • Operation 502 depicts ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content.
  • incoming audiovisual data streams containing programming and advertisement content may be downlinked from satellites to which a national network broadcast center for a channel has uplinked the data stream.
  • Data streams may also be received from other sources, e.g. via downlinking from other sources, received via a fiber optic connection, received using conventional VHF, UHF, or microwave antennas, received over a data network such as the internet, etc.
  • Data associated with the data streams may be stored in a media data store which may also be known as a primary matching system database.
  • the operations by which the data associated with the data streams may be stored in a media data store may include operations described in a parent application, U.S. Patent Application No. 12/788,721 (now U.S. Patent 8,595,781), "METHODS FOR IDENTIFYING VIDEO SEGMENTS AND DISPLAYING CONTEXTUAL TARGETED CONTENT ON A CONNECTED TELEVISION” ("the '781 patent”); and/or in related U.S. Patent Application No. **/***,***, "SYSTEMS AND METHODS FOR ADDRESSING A MEDIA DATABASE USING DISTANCE ASSOCIATIVE HASHING” filed concurrently with the instant application and/or in related U.S. Patent Application No. **/*** ***, "SYSTEMS AND METHODS FOR IDENTIFYING VIDEO SEGMENTS FOR DISPLAYING CONTEXTUALLY RELEVANT CONTENT" ("the related applications”).
  • operation 504 depicts determining a candidate segment, the candidate segment including at least one or more sequential frames from the at least one ingested audiovisual stream.
  • a possible match is chosen, perhaps via a content search process on the incoming feed.
  • the possible match may represent any contiguous segment of frames having just been ingested on any channel feed for which a similar or identical contiguous segment of frames already exists in the media content database.
  • the possible match may represent an advertisement (duplicates of which in a media content database without an advertisement detection means would be expected as ads repeat frequently) or another short segment of interest such as a public service announcement.
  • the possible match may then be evaluated via a three step process which may include evaluating a possible match for length, evaluating a possible match against the already-existing segment of frames for closeness of fingerprints using more rigorous matching requirements, and evaluating the possible match against the already-existing frames for closeness of fingerprints using less rigorous matching requirements, helping to identify borders of the possible match.
  • the possible match is returned as a candidate segment [0055]
  • operation 506 depicts testing the determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • Figure 5 also illustrates an alternative embodiment of the example operational flow 500.
  • Figure 5 illustrates an example embodiment where operational flow 500 may include at least one additional operation 508.
  • Operation 508 illustrates testing the determined candidate segment for at least one match in the data store of program content and, if testing the candidate segment returns at least one match in the data store of program content, at least removing at least some data associated with the candidate segment from the data store of program content and storing at least some data associated with the candidate segment in the data store of known advertisements.
  • the result of operation 506 is that the candidate segment suspected to be an ad is not previously known via checking the ad database
  • data associated with the candidate segment is checked against the media content database. If the candidate segment suspected to be an ad is also found in the media content database, the data associated with the segment found in the media content database is removed. Further, the data associated with the segment is placed in the data store of known advertisements. The operational flow may then proceed to an end operation.
  • Figure 6 illustrates alternative embodiments of the example operational flow 500 of Figure 5.
  • Figure 6 illustrates an example embodiment where operation 502 may include at least one additional operation. Additional operations may include operation 602, operation 604, operation 606, and/or operation 608.
  • Operation 602 illustrates receiving one or more indications of a frame of the ingested audiovisual data stream. For example, as shown in and/or described with respect to Figures 1 through 3, data associated with a particular frame from the incoming data stream is selected.
  • operation 604 illustrates analyzing the one or more indications of a frame, including at least determining whether the one or more indications could be a starting frame of a candidate segment.
  • the data associated with the particular frame may be checked for the presence of particular signatures which would indicate that the particular frame could be the start of a commercial.
  • operation 606 illustrates if a starting frame is determined, analyzing one or more frames received subsequent to the starting frame, including at least determining whether one of the one or more frames received subsequent to the starting frame could be an ending frame. For example, as shown in and/or described with respect to Figures 1 through 3, if signatures are detected that suggest the frame may be the first frame of a commercial, the process begins analyzing successive frames received subsequent to the purported starting frame to see whether any of the successive frames might include the particular signatures.
  • operation 608 illustrates if an ending frame is determined, establishing (i) the starting frame, (ii) the one or more frames received subsequent to the starting frame and previous to the ending frame, and (iii) the ending frame as the candidate segment.
  • an ending frame is determined, establishing (i) the starting frame, (ii) the one or more frames received subsequent to the starting frame and previous to the ending frame, and (iii) the ending frame as the candidate segment.
  • Figure 6 illustrates a further alternative embodiment of the operation 604.
  • Operation 604 may include at least one additional operation 610.
  • Operation 610 illustrates determining whether a frame is at least one of a monochromatic frame or a frame having one or more substantially different fingerprint values from an immediately-previous frame and, if a frame is at least one of a monochromatic frame or a frame having one or more substantially different fingerprint values from an immediately- previous frame, establishing the frame as at least one of a starting frame or an ending frame.
  • a signature suggesting a frame may be a starting frame include that the frame is monochromatic (e.g. solid black, solid white), as commercials often begin with one or more all black frames, for example.
  • a starting frame for a commercial could be represented by a "scene change.”
  • two successive commercials, or a program followed by a commercial most likely include differing scenes.
  • a scene change which may represent a transition from a program to a commercial or a transition between commercials. Detecting a significant difference between two frames may be accomplished at least partially by one or more operations disclosed in the 781 patent and/or the related applications.
  • a scene change is not dispositive of a commercial alone, merely that such a frame might represent a starting frame.
  • Figure 7 illustrates alternative embodiments of the example operational flow 500.
  • Figure 7 illustrates an example embodiment where operation 504 may include at least one additional operation. Additional operations may include operation 702, operation 704, operation 706 and/or operation 708.
  • Operation 702 illustrates receiving one or more indications of a frame of the ingested audiovisual data stream. For example, as shown in and/or described with respect to Figures 1 through 3, data associated with a particular frame from the incoming data stream is selected.
  • operation 704 illustrates comparing data associated with a contiguous sequence of ingested frames ending with the most recently received frame with data associated with one or more contiguous sequences of frames previously stored in the data store of program content. For example, as shown in and/or described with respect to Figures 1 through 3, data associated with a segment of contiguous frames having just been ingested and ending in the particular frame is checked against the media content data store to determine whether there are any segments of contiguous frames in the data store which may match the segment just ingested and ending in the particular frame.
  • operation 706 illustrates providing one or more indications of one or more contiguous sequences of frames previously stored in the data store of program content based at least partially on the comparing data.
  • the matching operation 704 may return data associated with one or more at least partially matching contiguous segments.
  • Matches, or partial matches, of a contiguous segment of frames having just been ingested with one or more contiguous segments of frames in the media content database may indicate that the contiguous segment of frames having just been ingested may be a commercial. So, too, may be the at least partially matched one or more contiguous segments of frames in the media content database.
  • the matching operation does not search the media content database for exact, frame -by-frame and pixel-by-pixel matches. Rather, suspected matches are returned from the media content database that are at least partially related to the segment just ingested, the matching and/or returning perhaps via operations disclosed in the '781 patent and/or the related applications.
  • operation 708 illustrates for each of the one or more indicated contiguous sequences of frames, determining whether the contiguous sequence of frames is an advertisement. For example, as shown in and/or described with respect to Figures 1 through 3, one or more tests may be applied to the contiguous sequence of frames, which is at this stage a suspected or purported advertisement, the one or more tests applied to confirm the suspicion that the contiguous sequence of frames is an advertisement.
  • Figure 7 illustrates a further alternative embodiment of the operation 708.
  • Operation 708 may include at least one additional operation 710.
  • Operation 710 illustrates evaluating at least one of a length in seconds or a count in frames associated with the contiguous sequence of frames and, if the at least one of a length in seconds or a count in frames is substantially similar to a standard advertisement length, establishing the contiguous sequence of frames as a candidate segment. For example, as shown in and/or described with respect to Figures 1 through 3, the contiguous sequence of frames representing the purported advertisement is checked for length. If the length is near a common advertisement length (e.g., 30 seconds, 15 seconds, 60 seconds, or other common ad lengths), then the contiguous sequence of frames may still be considered a suspected advertisement. If the length is not near a common advertisement length (e.g.
  • the contiguous sequence of frames is considered less likely to be an advertisement and/or is no longer considered to be an advertisement.
  • the contiguous sequence of frames may still be considered a suspected advertisement.
  • a common number of frames may be, for example, 29.997 frames per second times 30 seconds, or approximately 900 frames.
  • the tested length may be exactly the duration or number of frames commonly used in an advertisement, or may be near the duration or number of frames commonly used in an advertisement (within two or three seconds, or within 60-90 frames, e.g.).
  • a matching algorithm used to return candidates from a media content database may return candidates which do not have exactly the same contiguous length (e.g.
  • Operation 710 may represent at least a portion of Step 1 disclosed elsewhere herein.
  • Figure 8 illustrates an operational flow 800 representing further alternative example operations continuing the example operational flow 500 of Figure 5.
  • Operational flow 800 may include operation 802, operation 804, and/or operation 806.
  • Operation 802 illustrates adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a lower returned number of suspects. For example, as shown in and/or described with respect to Figures 1 through 3, matching of data associated with the suspected advertisement and data associated with the one or more contiguous segments returned from the media content database is compared again for one or more possible matches.
  • additional matching may be completed comparing the purported advertisement with a relatively small number of search results, the additional matching completed using tighter tolerances for matching (again, perhaps via operations disclosed via the '781 patent and/or the related applications). Matching using tighter tolerances may be associated with more computationally-intensive operations; however, when used to compare smaller numbers of segments, the additional computational burden is within acceptable limits.
  • operation 804 illustrates matching the candidate segment with the one or more contiguous sequences of frames previously stored in the data store based at least partially on the adjusted at least one threshold.
  • the matching operation of the data associated with the purported advertisement with the data associated with the possible matches is completed with the tighter tolerances established in operation 802.
  • Operations 802 and 804 may represent at least a portion of Step 2 disclosed elsewhere herein.
  • One or more of the possible matches previously returned may be removed from the retrieved matches based at least partially on the matching with tighter tolerance.
  • operation 806 illustrates if the candidate segment matches the one or more contiguous sequences of frames previously stored in the data store based at least partially on the adjusted at least one threshold, determining starting and ending points of the candidate segment. For example, as shown in and/or described with respect to Figures 1 through 3, any matches previously retrieved from the media content database are checked against the purported advertisement again. An effect of this additional check may be to identify the boundaries of the purported commercial (i.e. to trim any superfluous frames from the beginning or end of the purported commercial or add back any missing frames from the beginning or end of the purported commercial, both via the comparison with the matches previously retrieved from the media content database). Operation 806 may, at least partially, be related to Step 3 disclosed elsewhere herein.
  • Figure 8 further illustrates an example embodiment where operation 802 may include at least one additional operation. Additional operations may include operation 808 and/or operation 810.
  • Operation 808 illustrates adjusting at least one radius associated with a path pursuit algorithm, the adjusted at least one radius associated with a lower returned number of suspects.
  • the tolerance may be made tighter via adjusting a radius associated with PPLEB searching and/or a path pursuit algorithm, perhaps via operations disclosed in the '781 patent and/or the related applications.
  • operation 810 illustrates adjusting at least one duration related to at least one bin associated with a path pursuit algorithm, the adjusted at least one radius associated with a lower returned number of suspects.
  • the tolerance may be made tighter via adjusting a duration radius associated with PPLEB searching and/or a path pursuit algorithm, perhaps via operations disclosed in the '781 patent and/or the related applications.
  • the duration may, for example, relate to the amount of time before tokens are dropped from time bins in a time discount binning arrangement.
  • the duration may, for example, relate a time-to-live value associated with one or more tokens of time bins in a time discount binning arrangement.
  • Figure 8 further illustrates an example embodiment where operation 806 may include at least one additional operation. Additional operations may include operation 812, operation 814, and/or operation 816.
  • Operation 812 illustrates adjusting at least one threshold associated with matching, the adjusted at least one threshold associated with a higher returned number of suspects. For example, as shown in and/or described with respect to Figures 1 through 3, tolerances adjusted to be tighter in operation 802 are loosened for additional matching which likely includes matching the purported advertisement with fewer retrieved matches from the media content database owing to the removal of retrieved matches via the tighter tolerance match of operation 804.
  • operation 814 illustrates comparing one or more indications associated with each frame in the candidate segment with one or more indications associated with a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, the comparing based at least partially on the adjusted at least one threshold.
  • the purported advertisement and the remaining matches are compared again using the looser tolerance(s) (e.g. radius, duration, others described in the '781 patent or related applications, etc.).
  • operation 816 illustrates testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing. For example, as shown in and/or described with respect to Figures 1 through 3, boundaries of the purported advertisement may be more accurately determined during this test in which each point of the two samples may be farther apart, perhaps in time or distance, for example.
  • Figure 9 illustrates a further alternative embodiment of the operation 816, which may include at least one additional operation.
  • Operation 816 may include operation 902, operation 904, operation 906, and/or operation 908.
  • Operation 902 illustrates if any frame of the candidate segment does not have a corresponding match in the one or more contiguous sequences of frames previously stored in the data store, dropping the frame of the candidate segment without a corresponding match from the one or more contiguous sequences of frames previously stored in the data store. For example, as shown in and/or described with respect to Figures 1 through 3, excess frames, perhaps at the beginning or end of the purported advertisement, or perhaps in the middle of the purported advertisement, which do not have a corresponding match in the segment retrieved from the media content database may be dropped.
  • Operation 904 illustrates if any frame of the one or more contiguous sequences of frames previously stored in the data store does not have a corresponding match in the candidate segment, adding the frame of the one or more contiguous sequences of frames previously stored in the data store to the candidate segment. For example, as shown in and/or described with respect to Figures 1 through 3, frames found in the segment retrieved from the media content database which do not have a corresponding match in the purported advertisement may be added to the segment representing the purported advertisement, perhaps at the beginning or end of the purported advertisement and/or the middle of the purported advertisement.
  • Operation 906 testing for inconsistencies between each frame in the candidate segment and a corresponding frame in the one or more contiguous sequences of frames previously stored in the data store, based at least partially on the comparing. For example, as shown in and/or described with respect to Figures 1 through 3, the purported advertisement is compared with the one or more surviving matches retrieved from the media content database which passed through steps 1 and 2 for any inconsistencies between them, which may comprise at least a portion of Step 3 disclosed elsewhere herein.
  • Operation 908 illustrates remediating any inconsistencies found via testing, the remediating operable to identify borders of the candidates.
  • the results of operation 906 help identify the borders of the suspected television commercial and are evaluated to have no missing points (i.e. all points in the two samples match) and to have beginning and end boundaries that are within a time threshold of the originally suspected commercial (i.e. if the original possible match was 15 seconds long then the results of the loose content search can't be 30 seconds long, etc.).
  • Figure 10 illustrates alternative embodiments of the example operational flow 500 of Figure 5.
  • Figure 6 illustrates an example embodiment where operation 502 and operation 506 may include at least one additional operation. Additional operations may include operation 1002.
  • Operation 1002 illustrates ingesting at least two audiovisual streams, including at least storing at least some data associated with one or more frames of at least one of the at least two audiovisual streams into a data store of program content, the at least some data including at least one indication of the audiovisual stream from which the one or more frames were received, and testing the determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, the at least one match related to any of the at least two audiovisual streams, at least removing at least some data associated with the candidate segment from the data store of program content.
  • more than one channel is downlinked and/or otherwise received and data associated with the data stream from the channel is stored in the media content database, the data associated with each channel downlinked and stored in parallel or substantially in parallel.
  • a particular commercial could be received on any or all of the more than one channel, resulting in potentially many instances of data associated with the particular commercial stored in the media content database.
  • Operations disclosed herein related to determining data associated with advertisements in the media content database may serve to identify and/or process the data associated with the particular advertisement no matter which channel the particular advertisement ran on and/or what time the particular advertisement ran.
  • Figure 11 illustrates alternative embodiments of the example operational flow 500 of Figure 5.
  • Figure 11 illustrates an example embodiment where operation 504 may include at least one additional operation. Additional operations may include operation 1102, operation 1104, operation 11011, and/or operation 1108.
  • Operation 1102 illustrates confirming a candidate segment having a low threshold match at least partially based on at least one duration of the candidate segment.
  • a purported advertisement aka a suspected advertisement, suspected commercial, suspected television commercial, suspected television advertisement
  • the segment may be selected as a purported advertisement as a "low threshold match.”
  • a desired target duration may be at least five seconds (because commercials of fewer than five seconds are extremely rare or non-existent) and/or less than 60 or 120 seconds (because commercials of longer than 60 or 120 seconds are also extremely rare or non-existent).
  • This is not a dispositive test; rather, the duration or corresponding number of frames is a first indication, with subsequent tests intended to confirm the first indication (i.e. confirm with a high threshold).
  • operation 1104 illustrates confirming the candidate segment having a high threshold match at least partially based on a match of one or more fingerprints of the candidate segment with a known advertisement.
  • data associated with one or more frames of the purported advertisement fingerprints, perhaps
  • the fingerprints and/or comparing may result from operations disclosed in the '781 patent and/or the related operations.
  • One result of comparing the data sets may be a stronger indication, or even a confirmation, that the purported commercial matches the segment from the database (a "high threshold match").
  • operation 1106 illustrates determining a segment which may be at least one of an advertisement, a commercial, a public service announcement, a promotion, at least a portion of an ad break, at least a portion of an ad pod, or an upcoming television programming promotion.
  • segments of interest disclosed in the instant application may be known as one or more of an advertisement, a commercial, a public service announcement, a promotion, at least a portion of an ad break, at least a portion of an ad pod, or an upcoming television programming promotion.
  • Other nomenclature denoting the segment as a segment of interest for the purposes of this application may exist and all such nomenclature is within the scope of this application.
  • operation 1108 illustrates determining a candidate segment, the candidate segment including at least one or more sequential video frames from the at least one ingested audiovisual stream.
  • candidate segments of contiguous frames ingested from the data stream can include segments of contiguous video frames.
  • the systems and methods disclosed elsewhere herein could relate to other aspects of a data stream, for example, audio frames, metadata associated with frames of the data stream, or other such embodiments.
  • Figure 12 illustrates an exemplary computer program product 1200 which may include at least one non-transitory computer-readable medium. Further illustrated in Figure 12 are instructions 1204 of computer program product 1200. Instructions 1204 illustrate one or more instructions for ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; one or more instructions for determining a candidate segment, the candidate segment including at least one or more sequential frames from at least one ingested audiovisual stream; and one or more instructions for testing a determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • Instructions 1204 illustrate one or more instructions for ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; one or more instructions for
  • a computer program product may include one or more instructions encoded on and/or stored by one or more non-transitory computer-readable media.
  • the one or more instructions may, when executed by one or more processing devices, cause the one or more processing devices to perform operations including ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content; determining a candidate segment, the candidate segment including at least one or more sequential frames from at least one ingested audiovisual stream; and testing a determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • the foregoing operations may be similar at least in part and/or be substantially similar to (but are not limited to) corresponding operations disclosed elsewhere herein.
  • FIG. 13 illustrates an exemplary system 1300.
  • System 1300 may include circuitry 1302, circuitry 1304, and/or circuitry 1306.
  • Circuitry 1302 illustrates circuitry configured for ingesting at least one audiovisual stream, including at least storing at least some data associated with one or more frames of the audiovisual stream into a data store of program content.
  • circuitry 1302 may cause operations with an effect similar at least in part and/or substantially similar to (but not limited to) corresponding operations disclosed elsewhere herein.
  • circuitry 1304 illustrates circuitry configured for determining a candidate segment, the candidate segment including at least one or more sequential frames from at least one ingested audiovisual stream.
  • circuitry 1304 may cause operations with an effect similar at least in part and/or substantially similar to (but not limited to) corresponding operations disclosed elsewhere herein.
  • circuitry 1306 illustrates circuitry configured for testing a determined candidate segment for at least one match in a data store of known advertisements and, if testing the candidate segment returns at least one match in the data store of known advertisements, at least removing at least some data associated with the candidate segment from the data store of program content.
  • circuitry 1306 may cause operations with an effect similar at least in part and/or substantially similar to (but not limited to) corresponding operations disclosed elsewhere herein.
  • Embodiments of the subject matter described in this specification can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a tangible program carrier for execution by, or to control the operation of, data processing apparatus.
  • the computer readable medium can be a machine readable storage device, a machine readable storage substrate, a memory device, or a combination of one or more of them.
  • a computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
  • a computer program does not necessarily correspond to a file in a file system.
  • a program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code).
  • a computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a suitable communication network.
  • the essential elements of a computer are a processor for performing instructions and one or more memory devices for storing instructions and data.
  • a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
  • mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks.
  • processors suitable for the execution of a computer program include, by way of example only and without limitation, both general and special purpose microprocessors, and any one or more processors of any kind of digital computer.
  • a processor will receive instructions and data from a read only memory or a random access memory or both.
  • embodiments of the subject matter described in this specification can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, e.g., a mouse or a trackball, by which the user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • keyboard and a pointing device e.g., a mouse or a trackball
  • Other kinds of devices can be used to provide for interaction with a user as well.
  • feedback provided to the user can be any form of sensory feedback, e.g., visual feedback, auditory feedback, or tactile feedback
  • input from the user can be received in any form, including acoustic, speech, or tactile input.
  • Embodiments of the subject matter described in this specification can be implemented in a computing system that includes back end component(s) including one or more data servers, or that includes one or more middleware components such as application servers, or that includes a front end component such as a client computer having a graphical user interface or a Web browser through which a user or administrator can interact with some implementations of the subject matter described is this specification, or any combination of one or more such back end, middleware, or front end components.
  • the components of the system can be interconnected by any form or medium of digital data communication, such as a communication network.
  • the computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client server relationship to each other.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Databases & Information Systems (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Computer Security & Cryptography (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

La présente invention concerne un système et un procédé permettant la détection et le traitement automatisés et en temps réel de messages commerciaux, d'annonces de services publics ou de segments de programmation télévisuelle répétés, similaires et de courte durée, apparaissant dans un ou plusieurs flux vidéo de diffusion. Un traitement est utilisé, qui identifie de possibles segments commerciaux en identifiant des segments vidéo distincts qui présentent, entre autres attributs, de courtes durées spécifiques. Des segments vidéo qui se révèlent avoir ces caractéristiques sont considérés comme étant vraisemblablement des messages commerciaux, des promotions ou des annonces de services publics télévisuels et sont stockés dans une base de données des publicités télévisuelles qui est séparée de la base de données principale du contenu télévisuel. Une vidéo entrante provenant d'une pluralité de sources de programmation télévisuelle est traitée sous forme d'empreintes et placée dans une base de données maîtresse du contenu télévisuel. Dans le même temps, ladite programmation entrante est testée par rapport à des correspondances dans une base de données des publicités télévisuelles. Si une correspondance est trouvée, la publicité télévisuelle présumée est retirée de la base de données maîtresse du contenu.
PCT/US2014/030795 2013-03-15 2014-03-17 Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenu automatisée WO2014145938A1 (fr)

Priority Applications (23)

Application Number Priority Date Filing Date Title
CN201480015936.XA CN105052161B (zh) 2013-03-15 2014-03-17 实时电视广告检测的系统和方法
MX2015012510A MX356884B (es) 2013-03-15 2014-03-17 Sistemas y metodos para direccionar una base de datos de medios usando cifrado asociativo en distancia.
BR112015023369-4A BR112015023369B1 (pt) 2013-03-15 2014-03-17 Sistema e método implementado por computador
MX2020001441A MX2020001441A (es) 2013-03-15 2014-03-17 Sistemas y metodos para direccionar una base de datos de medios usando troceo asociativo en distancia.
CN201811395356.4A CN110083739B (zh) 2013-03-15 2014-03-17 用于使用距离关联性散列法对媒体数据库定址的系统和方法
CA3173549A CA3173549A1 (fr) 2013-03-15 2014-03-17 Systemes et procedes d'identification de segments video pour afficher un contenu presentant une pertinence contextuelle
CA2906173A CA2906173C (fr) 2013-03-15 2014-03-17 Systemes et procedes d'identification de segments video pour afficher un contenu presentant une pertinence contextuelle
PCT/US2014/030782 WO2014145929A1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés pour interroger une base de données multimédia à l'aide d'un hachage associatif à distance
MX2015012512A MX365827B (es) 2013-03-15 2014-03-17 Sistemas y métodos de identificar segmentos de vídeo para visualizar un contenido contextualmente pertinente.
BR112015023389-9A BR112015023389B1 (pt) 2013-03-15 2014-03-17 Método e sistema para identificar segmentos de vídeo para exibir conteúdo contextualmente relevante
CA2906192A CA2906192C (fr) 2013-03-15 2014-03-17 Systemes et procedes permettant de detecter en temps reel une publicite televisuelle en utilisant une base de donnees de reconnaissance de contenu automatisee
BR112015023380-5A BR112015023380B1 (pt) 2013-03-15 2014-03-17 Sistema e método para detecção de propaganda detelevisão em tempo real usando banco de dados de reconhecimento de conteúdo automatizado
PCT/US2014/030805 WO2014145947A1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés d'identification de segments vidéo pour afficher un contenu présentant une pertinence contextuelle
CA2906199A CA2906199C (fr) 2013-03-15 2014-03-17 Systemes et procedes pour interroger une base de donnees multimedia a l'aide d'un hachage associatif a distance
MX2015012511A MX366327B (es) 2013-03-15 2014-03-17 Sistemas y metodos para la deteccion de anuncios de television en tiempo real usando una base de datos de reconocimiento de contenido automatizado.
EP14763506.4A EP2982131B1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenu automatisée
EP19166400.2A EP3534615B1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenus automatisée
CN201480017043.9A CN105144141B (zh) 2013-03-15 2014-03-17 用于使用距离关联性散列法对媒体数据库定址的系统和方法
CL2015002623A CL2015002623A1 (es) 2013-03-15 2015-09-11 Sistemas y métodos para identificar segmentos de video para visualizar un contenido contextualmente pertinente
CL2015002621A CL2015002621A1 (es) 2013-03-15 2015-09-11 Sistemas y métodos para direccionar una base de datos de medios usando troceo asociativo en distancia.
MX2019007031A MX2019007031A (es) 2013-03-15 2015-09-11 Sistemas y metodos para identificar segmentos de video para visualizar un contenido contextualmente pertinente.
HK16105168.7A HK1218193A1 (zh) 2013-03-15 2016-05-05 用於使用自動化內容識別數據庫的實時電視廣告檢測的系統和方法
HK16105782.3A HK1217794A1 (zh) 2013-03-15 2016-05-20 用於使用距離關聯性散列法對媒體數據庫定址的系統和方法

Applications Claiming Priority (18)

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/US2014/030805 WO2014145947A1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés d'identification de segments vidéo pour afficher un contenu présentant une pertinence contextuelle
US14/217,375 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 (fr) 2013-03-15 2014-03-17 Systèmes et procédés pour interroger une base de données multimédia à l'aide d'un hachage associatif à distance
US14/217,039 2014-03-17
USPCT/US2014/30782 2014-03-17
US14/217,425 US9071868B2 (en) 2009-05-29 2014-03-17 Systems and methods for improving server and client performance in fingerprint ACR systems
US14/217,435 US9094715B2 (en) 2009-05-29 2014-03-17 Systems and methods for multi-broadcast differentiation
US14/217,425 2014-03-17
US14/217,435 2014-03-17
US14/217,075 US9055309B2 (en) 2009-05-29 2014-03-17 Systems and methods for identifying video segments for displaying contextually relevant content
USPCT/US2014/30805 2014-03-17
US14/217,075 2014-03-17
US14/217,375 US9094714B2 (en) 2009-05-29 2014-03-17 Systems and methods for on-screen graphics detection

Publications (1)

Publication Number Publication Date
WO2014145938A1 true WO2014145938A1 (fr) 2014-09-18

Family

ID=54261403

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2014/030795 WO2014145938A1 (fr) 2013-03-15 2014-03-17 Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenu automatisée

Country Status (7)

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

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9154942B2 (en) 2008-11-26 2015-10-06 Free Stream Media Corp. Zero configuration communication between a browser and a networked media device
US9258383B2 (en) 2008-11-26 2016-02-09 Free Stream Media Corp. Monetization of television audience data across muliple screens of a user watching television
US9386356B2 (en) 2008-11-26 2016-07-05 Free Stream Media Corp. Targeting with television audience data across multiple screens
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
US9560425B2 (en) 2008-11-26 2017-01-31 Free Stream Media Corp. Remotely control devices over a network without authentication or registration
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
US9986279B2 (en) 2008-11-26 2018-05-29 Free Stream Media Corp. Discovery, access control, and communication with networked services
EP3286757A4 (fr) * 2015-04-24 2018-12-05 Cyber Resonance Corporation Procédés et systèmes permettant de réaliser une analyse de signal pour identifier des types de contenu
WO2019006351A1 (fr) * 2017-06-30 2019-01-03 Sorenson Media, Inc. Certitude de trame destinée à une reconnaissance automatique de contenu
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
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
US10631068B2 (en) 2008-11-26 2020-04-21 Free Stream Media Corp. Content exposure attribution based on renderings of related content across multiple devices
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
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

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105975924A (zh) * 2016-04-29 2016-09-28 杭州当虹科技有限公司 一种基于视频帧数统计进行精确识别广告内容的回归测试方法
CN107633848A (zh) * 2016-07-19 2018-01-26 阿基米德（上海）传媒有限公司 一种通过识别音频指纹以去除广告的方法
CN106507141A (zh) * 2016-10-19 2017-03-15 天脉聚源（北京）科技有限公司 一种频道播出内容监控方法及装置
CN109522531B (zh) * 2017-09-18 2023-04-07 腾讯科技（北京）有限公司 文案生成方法和装置、存储介质及电子装置
CN107613326A (zh) * 2017-09-30 2018-01-19 深圳市鑫汇达机械设计有限公司 一种识别准确的电视广告识别系统
CN108959187B (zh) * 2018-04-09 2023-09-05 中国平安人寿保险股份有限公司 一种变量分箱方法、装置、终端设备及存储介质
CN111077326A (zh) * 2019-12-20 2020-04-28 中译语通文娱科技(青岛)有限公司 一种基于ai技术预感知能力的检测技术
CN112948636B (zh) * 2021-03-24 2022-09-27 黑龙江省能嘉教育科技有限公司 一种区域教育云资源共享系统及方法
CN114979691B (zh) * 2022-05-23 2023-07-28 上海影谱科技有限公司 一种体育赛事转播权益广告统计分析方法及系统

Citations (5)

* 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 (fr) * 2006-04-05 2007-10-11 Agency For Science, Technology And Research Appareil et procédé d'analyse de diffusion vidéo
US20090088878A1 (en) * 2005-12-27 2009-04-02 Isao Otsuka Method and Device for Detecting Music Segment, and Method and Device for Recording Data
WO2009150425A2 (fr) * 2008-06-10 2009-12-17 Half Minute Media Ltd Détection automatique de séquences vidéo répétitives

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102523482B (zh) * 2011-12-07 2014-07-23 中山大学 一种基于视频内容以及回归方法的广告监测技术
CN102760169A (zh) * 2012-06-13 2012-10-31 天脉聚源(北京)传媒科技有限公司 一种电视直播流中的广告段检测方法

Patent Citations (5)

* 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
US20090088878A1 (en) * 2005-12-27 2009-04-02 Isao Otsuka Method and Device for Detecting Music Segment, and Method and Device for Recording Data
WO2007114796A1 (fr) * 2006-04-05 2007-10-11 Agency For Science, Technology And Research Appareil et procédé d'analyse de diffusion vidéo
WO2009150425A2 (fr) * 2008-06-10 2009-12-17 Half Minute Media Ltd Détection automatique de séquences vidéo répétitives

Cited By (37)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9967295B2 (en) 2008-11-26 2018-05-08 David Harrison Automated discovery and launch of an application on a network enabled device
US10986141B2 (en) 2008-11-26 2021-04-20 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
US9258383B2 (en) 2008-11-26 2016-02-09 Free Stream Media Corp. Monetization of television audience data across muliple screens of a user watching television
US9154942B2 (en) 2008-11-26 2015-10-06 Free Stream Media Corp. Zero configuration communication between a browser and a networked media device
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
US9560425B2 (en) 2008-11-26 2017-01-31 Free Stream Media Corp. Remotely control devices over a network without authentication or registration
US9576473B2 (en) 2008-11-26 2017-02-21 Free Stream Media Corp. Annotation of metadata through capture infrastructure
US9589456B2 (en) 2008-11-26 2017-03-07 Free Stream Media Corp. Exposure of public internet protocol addresses in an advertising exchange server to improve relevancy of advertisements
US9591381B2 (en) 2008-11-26 2017-03-07 Free Stream Media Corp. Automated discovery and launch of an application on a network enabled device
US9686596B2 (en) 2008-11-26 2017-06-20 Free Stream Media Corp. Advertisement targeting through embedded scripts in supply-side and demand-side platforms
US9706265B2 (en) 2008-11-26 2017-07-11 Free Stream Media Corp. Automatic communications between networked devices such as televisions and mobile devices
US9703947B2 (en) 2008-11-26 2017-07-11 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
US9716736B2 (en) 2008-11-26 2017-07-25 Free Stream Media Corp. System and method of discovery and launch associated with a networked media device
US9838758B2 (en) 2008-11-26 2017-12-05 David Harrison Relevancy improvement through targeting of information based on data gathered from a networked device associated with a security sandbox of a client device
US9848250B2 (en) 2008-11-26 2017-12-19 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
US9854330B2 (en) 2008-11-26 2017-12-26 David Harrison Relevancy improvement through targeting of information based on data gathered from a networked device associated with a security sandbox of a client device
US9866925B2 (en) 2008-11-26 2018-01-09 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
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
US9386356B2 (en) 2008-11-26 2016-07-05 Free Stream Media Corp. Targeting with television audience data across multiple screens
US9167419B2 (en) 2008-11-26 2015-10-20 Free Stream Media Corp. Discovery and launch system and method
US10074108B2 (en) 2008-11-26 2018-09-11 Free Stream Media Corp. Annotation of metadata through capture infrastructure
US10032191B2 (en) 2008-11-26 2018-07-24 Free Stream Media Corp. Advertisement targeting through embedded scripts in supply-side and demand-side platforms
US10142377B2 (en) 2008-11-26 2018-11-27 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
US9986279B2 (en) 2008-11-26 2018-05-29 Free Stream Media Corp. Discovery, access control, and communication with networked services
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
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
US10419541B2 (en) 2008-11-26 2019-09-17 Free Stream Media Corp. Remotely control devices over a network without authentication or registration
US10425675B2 (en) 2008-11-26 2019-09-24 Free Stream Media Corp. Discovery, access control, and communication with networked services
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
US10631068B2 (en) 2008-11-26 2020-04-21 Free Stream Media Corp. Content exposure attribution based on renderings of related content across multiple devices
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
US10771525B2 (en) 2008-11-26 2020-09-08 Free Stream Media Corp. System and method of discovery and launch associated with a networked media device
US10791152B2 (en) 2008-11-26 2020-09-29 Free Stream Media Corp. Automatic communications between networked devices such as televisions and mobile devices
EP3286757A4 (fr) * 2015-04-24 2018-12-05 Cyber Resonance Corporation Procédés et systèmes permettant de réaliser une analyse de signal pour identifier des types de contenu
US10715863B2 (en) 2017-06-30 2020-07-14 The Nielsen Company (Us), Llc Frame certainty for automatic content recognition
WO2019006351A1 (fr) * 2017-06-30 2019-01-03 Sorenson Media, Inc. Certitude de trame destinée à une reconnaissance automatique de contenu
US11206446B2 (en) 2017-06-30 2021-12-21 Roku, Inc. Frame replacement without overrun

Also Published As

Publication number Publication date
BR112015023380A8 (pt) 2018-08-14
CN105052161A (zh) 2015-11-11
BR112015023380B1 (pt) 2023-03-28
HK1218193A1 (zh) 2017-02-03
CA2906192A1 (fr) 2014-09-18
CL2015002619A1 (es) 2016-04-15
MX2019008020A (es) 2019-09-04
CN105052161B (zh) 2018-12-28
MX2015012511A (es) 2016-01-12
CA2906192C (fr) 2020-10-27
MX366327B (es) 2019-07-05
BR112015023380A2 (pt) 2017-07-18

Similar Documents

Publication Publication Date Title
CA2906192C (fr) Systemes et procedes permettant de detecter en temps reel une publicite televisuelle en utilisant une base de donnees de reconnaissance de contenu automatisee
US8930980B2 (en) Systems and methods for real-time television ad detection using an automated content recognition database
EP3534615B1 (fr) Systèmes et procédés permettant de détecter en temps réel une publicité télévisuelle en utilisant une base de données de reconnaissance de contenus automatisée
US20140201774A1 (en) Systems and methods for multi-broadcast differentiation
AU2016291674B2 (en) Systems and methods for partitioning search indexes for improved efficiency in identifying media segments
US10614137B2 (en) System and method for detecting repeating content, including commercials, in a video data stream
US9628836B1 (en) System and method for removing erroneously identified TV commercials detected using automatic content recognition
US11659255B2 (en) Detection of common media segments
EP3776263B1 (fr) Système et procédé de détection de contenu répétitif, incluant des publicités, dans un flux de données vidéo à l'aide d'une reconnaissance de contenu automatisée sur la base de données audio et vidéo
US10805681B2 (en) System and method for detecting unknown TV commercials from a live TV stream
US10945030B2 (en) Detection of potential commercial by detection and analysis of transitions in video content

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 201480015936.X

Country of ref document: CN

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 14763506

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2906192

Country of ref document: CA

WWE Wipo information: entry into national phase

Ref document number: MX/A/2015/012511

Country of ref document: MX

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2014763506

Country of ref document: EP

REG Reference to national code

Ref country code: BR

Ref legal event code: B01A

Ref document number: 112015023380

Country of ref document: BR

WWE Wipo information: entry into national phase

Ref document number: 12016502242

Country of ref document: PH

ENP Entry into the national phase

Ref document number: 112015023380

Country of ref document: BR

Kind code of ref document: A2

Effective date: 20150914