专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08316302B2 Method and apparatus for annotating video content with metadata generated using speech recognition technology 有权
标题翻译：使用语音识别技术生成的元数据来注释视频内容的方法和装置
公开(公告)号：US08316302B2
公开(公告)日：2012-11-20
申请号：US11747584
申请日：2007-05-11
申请人： Kevin M. McKoen , Michael A. Grossman
发明人： Kevin M. McKoen , Michael A. Grossman
IPC分类号： G06F3/16
CPC分类号： G06F17/241 , G06F17/30781 , G06F17/30796 , G06F17/30817 , G10L15/26 , G10L15/265
摘要： A method and apparatus is provided for annotating video content with metadata generated using speech recognition technology. The method begins by rendering video content on a display device. A segment of speech is received from a user such that the speech segment annotates a portion of the video content currently being rendered. The speech segment is converted to a text-segment and the text-segment is associated with the rendered portion of the video content. The text segment is stored in a selectively retrievable manner so that it is associated with the rendered portion of the video content.
摘要翻译：提供了一种用于使用语音识别技术生成的元数据来注释视频内容的方法和装置。该方法开始于在显示设备上呈现视频内容。从用户接收到语音段，使得语音段注释当前正在呈现的视频内容的一部分。语音段被转换为文本段，并且文本段与视频内容的被渲染部分相关联。文本段以可选择地检索的方式存储，使得它与视频内容的被渲染部分相关联。

2. 发明申请

US20080281592A1 Method and Apparatus for Annotating Video Content With Metadata Generated Using Speech Recognition Technology 有权
标题翻译：使用语音识别技术生成的元数据来注释视频内容的方法和装置
公开(公告)号：US20080281592A1
公开(公告)日：2008-11-13
申请号：US11747584
申请日：2007-05-11
申请人： Kevin M. McKoen , Michael A. Grossman
发明人： Kevin M. McKoen , Michael A. Grossman
IPC分类号： G10L15/26 , G06F3/14
CPC分类号： G06F17/241 , G06F17/30781 , G06F17/30796 , G06F17/30817 , G10L15/26 , G10L15/265
摘要： A method and apparatus is provided for annotating video content with metadata generated using speech recognition technology. The method begins by rendering video content on a display device. A segment of speech is received from a user such that the speech segment annotates a portion of the video content currently being rendered. The speech segment is converted to a text-segment and the text-segment is associated with the rendered portion of the video content. The text segment is stored in a selectively retrievable manner so that it is associated with the rendered portion of the video content.
摘要翻译：提供了一种使用语音识别技术生成的元数据来注释视频内容的方法和装置。该方法开始于在显示设备上呈现视频内容。从用户接收到语音段，使得语音段注释当前正在呈现的视频内容的一部分。语音段被转换为文本段，并且文本段与视频内容的被渲染部分相关联。文本段以可选择地检索的方式存储，使得它与视频内容的被渲染部分相关联。

3. 发明授权

US07450180B2 Method for detecting interlaced material and field order 有权
标题翻译：检测交错材料和场顺序的方法
公开(公告)号：US07450180B2
公开(公告)日：2008-11-11
申请号：US11025029
申请日：2004-12-29
申请人： David M. Baylon , Kevin M. McKoen
发明人： David M. Baylon , Kevin M. McKoen
IPC分类号： H04N5/46
CPC分类号： H04N5/144 , H04N5/4401 , H04N7/012 , H04N21/44008
摘要： A (50) method and apparatus (110) for determining a scanning format of a frame of a video signal determines (52) if any interfield motion exists within the frame; and indicates (53) that the frame is interlaced scanned if interfield motion is detected and indicates (54) that the frame is progressive scanned if interfield motion is not detected. The determination is based on spatial correlation within and around one or more edges of one or more objects in the frame. This can be accomplished by identifying zig-zag or zipper effects near one or more edges of one or more objects in the frame, identifying motion between fields or identifying motion near one or more edges of one or more objects. A method (100) for determining a field order of two interlaced frames of a video sequence of frames assigns (101) one of the two interlaced frames to be a first frame and the other of the two interlaced frames to be a second frame and assembles (102) two new frames from the two interlaced frames by combining a bottom field of the first frame with the top field of the second frame and by combining a top field of the first frame with a bottom field of the second frame. The number of zipper points in each of the two new frames is then determined and compared. If the number of zipper points in the first frame is smaller than the number of zipper points in the second frame, that the field order of the two frames is top field first, otherwise the field order is bottom field first.
摘要翻译：用于确定视频信号的帧的扫描格式的（50）方法和装置（110）确定（52）如果帧内存在任何场间运动，并且指示（53）如果检测到场间运动，则帧被扫描，并且指示（54）如果没有检测到场间运动，则帧被逐行扫描。该确定基于帧中的一个或多个对象的一个或多个边缘内和周围的空间相关性。这可以通过在帧中的一个或多个对象的一个或多个边缘附近识别字形或拉链效应来实现，识别场之间的运动或识别在一个或多个对象的一个或多个边缘附近的运动。一种用于确定帧的视频序列的两个隔行帧的场顺序的方法（100）将（101）所述两个隔行帧中的一个分配为第一帧，并且将所述两个隔行帧中的另一个作为第二帧，并组装（102）通过将第一帧的底场与第二帧的顶场组合并且通过将第一帧的顶场与第二帧的底场组合来从两个隔行扫描帧中获得两个新帧。然后确定并比较两个新帧中的每一个中的拉链点的数量。如果第一帧中的拉链点的数量小于第二帧中的拉链点的数量，则两帧的场顺序首先是顶场，否则首先是场顺序是底场。

4. 发明授权

US08068175B2 Method for detecting interlaced material and field order 有权
标题翻译：检测交错材料和场顺序的方法
公开(公告)号：US08068175B2
公开(公告)日：2011-11-29
申请号：US11962880
申请日：2007-12-21
申请人： David M. Baylon , Kevin M. McKoen
发明人： David M. Baylon , Kevin M. McKoen
IPC分类号： H04N5/08
CPC分类号： H04N5/144 , H04N5/4401 , H04N7/012 , H04N21/44008
摘要： Field order in a sequence of video frames is determined based on magnitude or relative motion of a motion vector between a bottom field of a current frame and a top field of a next frame, and magnitude or relative motion of a motion vector between a top field of the current frame and a bottom field of the next frame. Field order of two interlaced frames of a video sequence is determined by assembling two new frames from the two interlaced frames by combining a bottom field of the first frame with a top field of the second frame and by combining a top field of the first frame with a bottom field of the second frame. The field order is top field first if the number of zipper points in the first new frame is smaller than the number of zipper points in the second new frame.
摘要翻译：视频帧序列中的场顺序基于当前帧的底场和下一帧的顶场之间的运动矢量的大小或相对运动以及顶场之间的运动矢量的大小或相对运动来确定的当前帧和下一帧的底部场。通过组合来自两个隔行扫描帧的两个新帧来确定视频序列的两个隔行帧的场顺序，该方法是将第一帧的底场与第二帧的顶场组合，并将第一帧的顶场与第二帧的底场。如果第一个新框架中的拉链点的数量小于第二个新框架中的拉链点的数量，则现场订单首先是顶部的。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式