发明名称 Method and system for syncronizing electronic program guides
摘要 A method for generating a time scheduling of a contents stream distributed to plural terminals. The contents stream is segmented in consecutive segments, each segment defining a corresponding program. The method includes: receiving auxiliary metadata including a planned time scheduling of the content stream which has been set in advance and monitoring at least a portion of a segment of the contents stream to extract corresponding content features therefrom, generating a corresponding fingerprint based on the extracted content features and assessing at least one among an actual start time and an actual end time of such segment based on a comparison between the fingerprint and a reference fingerprint associated with such segment, and updating the planned time scheduling based on the assessed at least one among the actual start time and actual end time to generate a time scheduling synchronized with the contents stream.
申请公布号 US9602854(B2) 申请公布日期 2017.03.21
申请号 US201013976773 申请日期 2010.12.29
申请人 TELECOM ITALIA S.p.A. 发明人 Francini Gianluca;Adami Nicola;Benini Sergio;Leonardi Riccardo
分类号 G06F3/00;G06F13/00;H04N5/445;H04N21/262;H04N21/234;H04N21/845 主分类号 G06F3/00
代理机构 Oblon, McClelland, Maier & Neustadt, L.L.P. 代理人 Oblon, McClelland, Maier & Neustadt, L.L.P.
主权项 1. A method for generating a time scheduling of a contents stream distributed to a plurality of terminals, the contents stream being segmented in consecutive segments, each segment defining a corresponding program, the method including: receiving auxiliary metadata comprising a planned time scheduling of the content stream which has been set in advance; partitioning each segment over time into a corresponding plurality of portions in accordance with video characteristics of said each segment; monitoring at least a selected subset of portions among the corresponding plurality of portions to extract corresponding video content features from the selected subset; generating a corresponding fingerprint based on the extracted video content features, the fingerprint including a set of the extracted video content features, wherein said generating the fingerprint includes gathering a respective collection of the video content features for each portion of the selected subset; assessing at least one among an actual start time and an actual end time of such segment based on a comparison between said fingerprint and a reference fingerprint associated with such segment and having a plurality of corresponding reference content features, said comparison between said fingerprint and said reference fingerprint including calculating a distance between each of the video content features and a corresponding one of the corresponding reference content features and calculating an average distance from the calculated distances, and wherein said assessing at least one among an actual start time and an actual end time includes comparing said average distance with a predetermined threshold; and updating the planned time scheduling based on the assessed at least one among the actual start time and the actual end time so as to generate a time scheduling synchronized with the contents stream.
地址 Milan IT