摘要:
A system, method and computer program utilize a distance associative hashing algorithmic means to provide a highly efficient means to rapidly address a large database. The indexing means can be readily subdivided into a plurality of independently-addressable segments where each such segment can address a portion of related data of the database where the sub-divided indexes of said portions reside entirely in the main memory of each of a multiplicity of server means. The resulting cluster of server means, each hosting an addressable sector of a larger database of searchable audio or video information, provides a significant improvement in the latency and scalability of an Automatic Content Recognition system, among other uses.
摘要:
A system and method for the identification of specific video segments in a video program, such as certain TV commercials, is presented. A means is described for an accelerated identification of the video segment of interest in conjunction with a means to communicate said information to a process in a remote television system such that the remote television system can anticipate the future start of said video segment of interest and display contextually related material in close proximity to the start of said video segment.
摘要:
A system and method for the identification of specific video segments in a video program, such as certain TV commercials, is presented. A means is described for an accelerated identification of the video segment of interest in conjunction with a means to communicate said information to a process in a remote television system such that the remote television system can anticipate the future start of said video segment of interest and display contextually related material in close proximity to the start of said video segment.
摘要:
A system, method and computer program utilize a distance associative hashing algorithmic means to provide a highly efficient means to rapidly address a large database. The indexing means can be readily subdivided into a plurality of independently-addressable segments where each such segment can address a portion of related data of the database where the sub-divided indexes of said portions reside entirely in the main memory of each of a multiplicity of server means. The resulting cluster of server means, each hosting an addressable sector of a larger database of searchable audio or video information, provides a significant improvement in the latency and scalability of an Automatic Content Recognition system, among other uses.
摘要:
A system and method are disclosed that improve the efficiency and performance of an Automatic Content Recognition (ACR) system. Several approaches are described that may be used alone or in combination to reduce total system computational costs related to the manner in which such an ACR means takes samples, called “fingerprints,” of digital content being played by a television display device and transmits said fingerprints to a remote server to be compared to a database of fingerprints from known programming. Methods are described for implementing such system performance enhancement including varying sampling rates and other resolution metrics during the process of creating such fingerprints and transmitting them to the database server. The system and method disclosed also describes how to reduce the probability that, when compared to samples from already-identified programming, such fingerprints are incorrectly identified as being of programming other than that which they are in fact derived from.
摘要:
A system and method for the automated real-time detection and processing of commercial messages, public service announcements or similar short-duration, repeated TV programming 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.
摘要:
A system and method for the automated real-time detection and processing of commercial messages, public service announcements or similar short-duration, repeated TV programming 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.
摘要:
A system and method are disclosed that improve the efficiency and performance of an Automatic Content Recognition (ACR) system. Several approaches are described that may be used alone or in combination to reduce total system computational costs related to the manner in which such an ACR means takes samples, called “fingerprints,” of digital content being played by a television display device and transmits said fingerprints to a remote server to be compared to a database of fingerprints from known programming. Methods are described for implementing such system performance enhancement including varying sampling rates and other resolution metrics during the process of creating such fingerprints and transmitting them to the database server. The system and method disclosed also describes how to reduce the probability that, when compared to samples from already-identified programming, such fingerprints are incorrectly identified as being of programming other than that which they are in fact derived from.
摘要:
A system and method is disclosed for resolving false positives in a centralized, real-time automatic content recognition system that is ingesting, fingerprinting, and attempting to match for recognition purposes, multiple streams of broadcast content that are simultaneously arriving from a plurality of sources. In particular, the problem of identifying which specific broadcast of certain programming has been matched, including the episode of a series, as well as the channel, time zone and time of broadcast and whether the programming is being watched “live” as broadcast or from a DVR time-shifted source, is addressed. This system and method enables the processing means of any connected TV viewing means to synchronize with a regional automated content recognition (ACR) center with regard to displaying at the correct time certain supplemental information or other media that may be associated with certain programming. It also reduces the probability of a false positive “recognition” of pre-recorded media or broadcasts from other time zones being displayed on the connected TV viewing means, and confusing such programming with the actual media with which the TV viewing device's processing means is intended to count, synchronize, interact with, or supplement.
摘要:
A system and method is disclosed for detecting locally-generated or other unknown graphics that are superimposed on a video program displayed on a television receiver or other like device. Devices external to a television receiver, such as a cable or satellite set-top box, can generate logos, electronic program guides, or other images that are then graphically overlaid on the television signal emanating from the device to the television's display. The system and method described herein provides a means to detect the presence of such on-screen graphics both to detect and identify graphical information and to also enable automated resolution of any interference among or between a plurality of video graphic sub-systems.