System and method for identifying and segmenting repeating media objects embedded in a stream

• US 6,766,523 B2
• Filed: 11/27/2002
• Issued: 07/20/2004
• Est. Priority Date: 05/31/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Herley, Cormac
• Primary Examiner(s): Srivastava, Vivek
• Assistant Examiner(s): BROWN, RUEBEN M
• Application Number:
  US10/307,100
• Publication Number:
  US 20030231868A1
• Time in Patent Office: 601 Days
• Field of Search: 725/18, 725/19, 725/22
• US Class Current: 725/19
• CPC Class Codes: H04H 60/37 for identifying segments of broadcast information, e.g. scenes or extracting programme ID
• CPC Class Codes: H04H 60/56 Arrangements characterised by components specially adapted for monitoring, identification or recognition covered by groups H04H60/29-H04H60/54

Abstract

An “object extractor” automatically identifies and segments repeating media objects in a media stream. “Objects” are any section of non-negligible duration, i.e., a song, video, advertisement, jingle, etc., which would be considered to be a logical unit by a human listener or viewer. Identification and segmentation of repeating objects is achieved by directly comparing sections of the media stream to identify matching portions of the stream, then aligning the matching portions to identify object endpoints. Alternately, a suite of object dependent algorithms is employed to target particular aspects of the stream for identifying possible objects within the stream. Confirmation of possible objects as repeating objects is achieved by automatically searching for potentially matching objects in a dynamic object database, followed by a detailed comparison to one or more of the potentially matching objects. Object endpoints are then determined by automatic alignment and comparison to other copies of that object.

Claims

1. A computer-implemented process for locating media objects in a media stream and determining temporal endpoints for each media object, comprising using a computing device to:

compute characteristic information for at least one segment of a media stream;

analyze the characteristic information to determine whether a media object is possibly present within any segment of the media stream;

store the location and characteristic information of any segment of the media stream in an object database when the analysis of the characteristic information indicates that at least part of a media object is possibly present within that segment of the media stream;

query the object database to locate potentially matching segments of the media stream;

compare potentially matching segments of the media stream to identify repeating segments within the media stream; and

automatically align and compare portions of the media stream centered on each repeating segment of the media stream to determine temporal endpoints for each media object in the media stream.