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. 发明申请

US20080193017A1 Method for detecting scene boundaries in genre independent videos 失效
标题翻译：用于检测流派独立视频中的场景边界的方法
公开(公告)号：US20080193017A1
公开(公告)日：2008-08-14
申请号：US11674750
申请日：2007-02-14
申请人： Kevin W. Wilson , Ajay Divakaran , Feng Niu , Naveen Goela , Isao Otsuka
发明人： Kevin W. Wilson , Ajay Divakaran , Feng Niu , Naveen Goela , Isao Otsuka
IPC分类号： G06K9/46
CPC分类号： G06T7/20 , G06N99/005
摘要： A computer implemented method detects scene boundaries in videos by first extracting feature vectors from videos of different genres. The feature vectors are then classified as scene boundaries using a support vector machine. The support vector machine is trained to be independent of the different genres of the videos.
摘要翻译：计算机实现的方法通过首先从不同类型的视频中提取特征向量来检测视频中的场景边界。然后使用支持向量机将特征向量分类为场景边界。支持向量机被训练为独立于不同类型的视频。

2. 发明授权

US07756338B2 Method for detecting scene boundaries in genre independent videos 失效
标题翻译：用于检测流派独立视频中的场景边界的方法
公开(公告)号：US07756338B2
公开(公告)日：2010-07-13
申请号：US11674750
申请日：2007-02-14
申请人： Kevin W. Wilson , Ajay Divakaran , Feng Niu , Naveen Goela , Isao Otsuka
发明人： Kevin W. Wilson , Ajay Divakaran , Feng Niu , Naveen Goela , Isao Otsuka
IPC分类号： G06K9/46 , G06K9/66
CPC分类号： G06T7/20 , G06N99/005
摘要： A computer implemented method detects scene boundaries in videos by first extracting feature vectors from videos of different genres. The feature vectors are then classified as scene boundaries using a support vector machine. The support vector machine is trained to be independent of the different genres of the videos.
摘要翻译：计算机实现的方法通过首先从不同类型的视频中提取特征向量来检测视频中的场景边界。然后使用支持向量机将特征向量分类为场景边界。支持向量机被训练为独立于不同类型的视频。

3. 发明授权

US08107541B2 Method and system for video segmentation 有权
标题翻译：视频分割方法和系统
公开(公告)号：US08107541B2
公开(公告)日：2012-01-31
申请号：US11593897
申请日：2006-11-07
申请人： Ajay Divakaran , Feng Niu , Naveen Goela
发明人： Ajay Divakaran , Feng Niu , Naveen Goela
IPC分类号： H04N5/262
CPC分类号： G06K9/00711 , G06F17/30787 , G10L25/48
摘要： A method segments a video. Audio frames of the video are classified with labels. Dominant labels are assigned to successive time intervals of consecutive labels. A semantic description is constructed for sliding time windows of the successive time intervals, in which the sliding time windows overlap in time, and the semantic description for each time window is a transition matrix determined from the dominant labels of the time intervals. A marker is determined from the transition matrices, in which a frequency of occurrence of the marker is between a low frequency threshold and a high frequency threshold. Then, the video is segmented at the locations of the markers.
摘要翻译：一种方法分割视频。视频的音频帧被分类为标签。主导标签分配给连续标签的连续时间间隔。对于连续时间间隔的滑动时间窗口构成语义描述，其中滑动时间窗口在时间上重叠，并且每个时间窗口的语义描述是从时间间隔的主要标签确定的转换矩阵。从标记的出现频率在低频阈值和高频阈值之间的转移矩阵确定标记。然后，视频在标记的位置被分割。

4. 发明申请

US20080124042A1 Method and system for video segmentation 有权
标题翻译：视频分割方法和系统
公开(公告)号：US20080124042A1
公开(公告)日：2008-05-29
申请号：US11593897
申请日：2006-11-07
申请人： Ajay Divakaran , Feng Niu , Naveen Goela
发明人： Ajay Divakaran , Feng Niu , Naveen Goela
IPC分类号： H04N5/93
CPC分类号： G06K9/00711 , G06F17/30787 , G10L25/48
摘要： A method segments a video. Audio frames of the video are classified with labels. Dominant labels are assigned to successive time intervals of consecutive labels. A semantic description is constructed for sliding time windows of the successive time intervals, in which the sliding time windows overlap in time, and the semantic description for each time window is a transition matrix determined from the dominant labels of the time intervals. A marker is determined from the transition matrices, in which a frequency of occurrence of the marker is between a low frequency threshold and a high frequency threshold. Then, the video is segmented at the locations of the markers.
摘要翻译：一种方法分割视频。视频的音频帧被分类为标签。主导标签分配给连续标签的连续时间间隔。对于连续时间间隔的滑动时间窗口构成语义描述，其中滑动时间窗口在时间上重叠，并且每个时间窗口的语义描述是从时间间隔的主要标签确定的转换矩阵。从标记的出现频率在低频阈值和高频阈值之间的转移矩阵确定标记。然后，视频在标记的位置被分割。

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