公开(公告)号：US06771885B1

公开(公告)日：2004-08-03

申请号：US09498884

申请日：2000-02-07

申请人： Lalitha Agnihotri ,  Nevenka Dimitrova ,  Thomas McGee ,  Nicholas J. Mankovich

发明人： Lalitha Agnihotri ,  Nevenka Dimitrova ,  Thomas McGee ,  Nicholas J. Mankovich

IPC分类号： H04N591

CPC分类号： H04N21/4334 ,  H04N5/782 ,  H04N21/44008 ,  H04N21/458 ,  H04N21/47214

摘要： A video signal is processed to generate one or more signatures associated with a broadcast program to be recorded by a recording device. The signatures are then processed to determine an actual start time and end time of the desired broadcast program, such that the program can be properly recorded despite delays or other changes in a pre-scheduled broadcast time of the program. One or more of the extracted signatures may be based at least in part on, e.g., a keyframe similarity measure, a histogram, one or more detected commercials, a transcript, a program logo or other detected object, detected text, and a sign-on or sign-off of the desired program. Other types of signatures can also be used.

摘要翻译： 视频信号被处理以产生与由记录装置记录的广播节目相关联的一个或多个签名。 然后处理签名以确定所需广播节目的实际开始时间和结束时间，使得尽管程序的预先计​​划的广播时间有延迟或其他改变，也可以适当地记录节目。 提取的签名中的一个或多个可以至少部分地基于例如关键帧相似性度量，直方图，一个或多个检测到的广告，抄本，节目标志或其他检测到的对象，检测到的文本和签名， 打开或关闭所需的程序。 也可以使用其他类型的签名。

公开(公告)号：US06721488B1

公开(公告)日：2004-04-13

申请号：US09451276

申请日：1999-11-30

申请人： Nevenka Dimitrova ,  Evgeniy Leyvi

发明人： Nevenka Dimitrova ,  Evgeniy Leyvi

IPC分类号： H04N591

CPC分类号： G11B27/28 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/324 ,  G11B27/328 ,  G11B27/34 ,  G11B2220/213 ,  G11B2220/216 ,  G11B2220/218 ,  G11B2220/2545 ,  G11B2220/2562 ,  G11B2220/2575 ,  G11B2220/90 ,  G11B2220/91 ,  G11B2220/913

摘要： A system that utilizes a determined time between characteristics from content for subsequently identifying the content and/or the corresponding content review position in the time domain. The system utilizes a database of previously stored time between characteristics from known content for matching to the determined time between characteristics from the content source. The characteristics may correspond to video tape indexing data, keyframe data, audio characteristics, text occurrences, and/or other known characteristics from the content. When a match is found between the determined time between characteristics and the stored times between characteristics, the system identifies the content. If corresponding time domain data is stored in the database, the system identifies the current content review position in the time domain. When the time between characteristics from the content does not match any of the times stored in the database, the system stores the current time between characteristics and corresponding content identifying information in the database for identifying the content at some subsequent time.

摘要翻译： 利用来自内容的特征之间的确定的时间的系统，用于随后在时域中识别内容和/或相应的内容审查位置。 系统利用来自已知内容的特征之间预先存储的时间的数据库，以匹配来自内容源的特征之间的确定时间。 特征可以对应于来自内容的视频磁带索引数据，关键帧数据，音频特性，文本出现和/或其他已知特征。 当在确定的特征之间的时间与特征之间的存储时间之间找到匹配时，系统识别内容。 如果对应的时域数据存储在数据库中，则系统会识别时域中的当前内容审查位置。 当来自内容的特征之间的时间与存储在数据库中的任何时间不匹配时，系统将当前时间存储在数据库中的特征与相应的内容识别信息之间，以便在某些后续时间识别内容。

公开(公告)号：US06714594B2

公开(公告)日：2004-03-30

申请号：US09854511

申请日：2001-05-14

申请人： Nevenka Dimitrova ,  Thomas McGee ,  Gerhardus Engbertus Mekenkamp ,  Edwin Salomons

发明人： Nevenka Dimitrova ,  Thomas McGee ,  Gerhardus Engbertus Mekenkamp ,  Edwin Salomons

IPC分类号： H04N712

CPC分类号： H04N21/44008 ,  H04N19/137 ,  H04N19/142 ,  H04N19/61 ,  H04N21/235 ,  H04N21/2353 ,  H04N21/435 ,  H04N21/812

摘要： The process of compressing video requires the calculation of a variety data that are used in the process of compression. The invention exploits some or all of these data for purposes of content detection. For example, these data may be leveraged for purposes of commercial detection. The luminance, motion vector field, residual values, quantizer, bit rate, etc. may all be used either directly or in combination, as signatures of content. A process for content detection may employ one or more features as indicators of the start and/or end of a sequence containing a particular type of content and other features as verifiers of the type of content bounded by these start/end indicators. The features may be combined and/or refined to produce higher-level feature data with good computational economy and content-classification utility.

摘要翻译： 压缩视频的过程需要计算在压缩过程中使用的各种数据。 本发明利用这些数据中的一些或全部用于内容检测的目的。 例如，这些数据可以用于商业检测的目的。 亮度，运动矢量场，残差值，量化器，比特率等都可以直接地或组合地用作内容的签名。 用于内容检测的过程可以使用一个或多个特征作为包含特定类型的内容和其他特征的序列的开始和/或结束的指示，作为由这些开始/结束指示符限定的内容类型的验证者。 这些特征可以被组合和/或改进以产生具有良好计算经济性和内容分类效用的较高级别的特征数据。

公开(公告)号：US06496228B1

公开(公告)日：2002-12-17

申请号：US09433258

申请日：1999-11-04

申请人： Thomas McGee ,  Nevenka Dimitrova ,  Jan Herman Elenbaas

发明人： Thomas McGee ,  Nevenka Dimitrova ,  Jan Herman Elenbaas

IPC分类号： H04N514

CPC分类号： G06F17/30802 ,  G06F17/30814 ,  G06F17/30858 ,  G06K9/00711 ,  G11B27/105 ,  G11B27/107 ,  G11B27/11 ,  G11B27/28 ,  G11B27/326 ,  G11B27/328 ,  G11B27/34 ,  G11B2220/2562 ,  G11B2220/65 ,  G11B2220/90 ,  H04N5/147 ,  H04N19/142 ,  H04N19/179 ,  H04N19/503 ,  H04N19/87 ,  H04N21/458 ,  H04N21/812

摘要： A video indexing system analyzes contents of source video and develops a visual table of contents using selected images. A system for detecting significant scenes detects video cuts from one scene to another, and static scenes based on DCT coefficients and macroblocks. A keyframe filtering process filters out less desired frames including, for example, unicolor frames, or those frames having a same object as a primary focus or one primary focuses. Commercials may also be detected and frames of commercials eliminated. The significant scenes and static scenes are detected based on a threshold which is set based on the category of the video.

摘要翻译： 视频索引系统分析源视频的内容，并使用选定的图像开发视觉目录。 用于检测重要场景的系统检测从一个场景到另一个场景的视频剪辑，以及基于DCT系数和宏块的静态场景。 关键帧过滤过滤过滤出不太期望的帧，包括例如单色帧，或具有与主要焦点相同的对象的帧或一个主要焦点。 也可以检测商业广告，消除商业广告。 基于基于视频的类别设置的阈值来检测重要场景和静态场景。

公开(公告)号：US6137544A

公开(公告)日：2000-10-24

申请号：US867140

申请日：1997-06-02

申请人： Nevenka Dimitrova ,  Thomas McGee ,  Jan Hermanus Elenbaas

发明人： Nevenka Dimitrova ,  Thomas McGee ,  Jan Hermanus Elenbaas

IPC分类号： H04N5/76 ,  G06F17/30 ,  H04N7/26 ,  H04N21/458 ,  H04N21/81 ,  H04N5/14

CPC分类号： G06K9/00711 ,  G06F17/30802 ,  G06F17/30814 ,  G06F17/30858 ,  H04N19/179 ,  H04N19/87 ,  H04N21/458 ,  H04N21/812

摘要： A video indexing system analyzes contents of source video and develops a visual table of contents using selected images. A system for detecting significant scenes detects video cuts from one scene to another, and static scenes based on DCT coefficients and macroblocks. A keyframe filtering process filters out less desired frames including, for example, unicolor frames, or those frames having a same object as a primary focus or one primary focuses. Commercials may also be detected and frames of commercials eliminated.

摘要翻译： 视频索引系统分析源视频的内容，并使用选定的图像开发视觉目录。 用于检测重要场景的系统检测从一个场景到另一个场景的视频剪辑，以及基于DCT系数和宏块的静态场景。 关键帧过滤过滤过滤出不太期望的帧，包括例如单色帧，或具有与主要焦点相同的对象的帧或一个主要焦点。 也可以检测商业广告，消除商业广告。

公开(公告)号：US6100941A

公开(公告)日：2000-08-08

申请号：US123444

申请日：1998-07-28

申请人： Nevenka Dimitrova ,  Thomas Mc Gee ,  Jan Hermanus Elenbaas ,  Eugene Leyvi ,  Carolyn Ramsey ,  David Berkowitz

发明人： Nevenka Dimitrova ,  Thomas Mc Gee ,  Jan Hermanus Elenbaas ,  Eugene Leyvi ,  Carolyn Ramsey ,  David Berkowitz

IPC分类号： H04N5/91 ,  G11B27/10 ,  G11B27/28 ,  H04H1/00 ,  H04H60/59 ,  H04N5/14 ,  H04N5/782 ,  H04N17/00

CPC分类号： H04N5/782 ,  G06F17/30814 ,  G06F17/30825 ,  G11B27/107 ,  G11B27/28 ,  H04H20/10 ,  H04H60/375 ,  H04H60/59 ,  H04N21/4325 ,  H04N21/4334 ,  H04N21/44008 ,  H04N21/812 ,  H04N5/147 ,  G11B2220/90 ,  Y10S358/908

摘要： A commercial detection apparatus includes a frame grab thread which acquires frames from an input data stream to be analyzed by a cut detector thread and a filter thread. A commercial detection thread determines whether a commercial has occurred from data created by the cut detector thread and the filter thread stored in a memory. A factor used by the commercial detection thread is whether a black frame has occurred. The input data stream is divided into a plurality of regions and then a maximum and minimum value for a section of these regions is determined and compared to one another. If the maximum and minimum values are close enough, and the maximum value is below a threshold, then the frame is deemed to be black. The commercial detection thread also looks at the average cut frame distance, cut rate, changes in the average cut frame distance, the absence of a logo, a commercial signature detection, brand name detection, a series of black frames preceding a high cut rate, similar frames located within a specified period of time before a frame being analyzed and character detection. During playback, the detected commercials are either skipped or substituted with alternate content.

摘要翻译： 商业检测装置包括从通过切断检测器线程和滤波器线程分析的输入数据流中获取帧的帧抓取线程。 商业检测线程确定是否从由切割检测器线程创建的数据和存储在存储器中的过滤器线程发生商业广告。 商业检测线程使用的因素是是否发生黑框。 输入数据流被分成多个区域，然后确定这些区域的一部分的最大值和最小值并将其彼此比较。 如果最大值和最小值足够近，并且最大值低于阈值，则该帧被认为是黑色的。 商业检测线程还查看平均切割帧距离，剪切速率，平均切割帧距离的变化，没有标志，商业签名检测，品牌名称检测，高切割率之前的一系列黑色帧， 位于分析帧之前的指定时间段内的类似帧和字符检测。 在播放期间，检测到的广告被跳过或替换为备用内容。