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

US20130108177A1 IMAGE MATCHING USING MOTION MANIFOLDS 有权
标题翻译：使用运动图像的图像匹配
公开(公告)号：US20130108177A1
公开(公告)日：2013-05-02
申请号：US13346662
申请日：2012-01-09
申请人： RAHUL SUKTHANKAR , JAY YAGNIK
发明人： RAHUL SUKTHANKAR , JAY YAGNIK
IPC分类号： G06K9/68
CPC分类号： G06K9/00758 , G06K9/6215 , G06K9/68 , G06T7/248 , G06T2207/30201 , G06T2207/30241
摘要： A motion manifold system analyzes a set of videos, identifying image patches within those videos corresponding to regions of interest and identifying patch trajectories by tracking the movement of the regions over time in the videos. Based on the patch identification and tracking, the system produces a motion manifold data structure that captures the way in which the same semantic region can have different visual representations over time. The motion manifold can then be applied to determine the semantic similarity between different patches, or between higher-level constructs such as images or video segments, including detecting semantic similarity between patches or other constructs that are visually dissimilar.
摘要翻译：运动歧管系统分析一组视频，识别与感兴趣区域相对应的那些视频内的图像补丁，并通过跟踪视频中随时间推移的区域的移动来识别斑块轨迹。基于补丁识别和跟踪，系统产生运动歧管数据结构，其捕获相同语义区域随时间具有不同视觉表示的方式。然后可以应用运动歧管以确定不同补丁之间的语义相似性，或者在诸如图像或视频段的更高级别的构造之间，包括检测补丁或视觉上相似的其他构造之间的语义相似性。

2. 发明申请

US20130113877A1 DETERMINING FEATURE VECTORS FOR VIDEO VOLUMES 有权
标题翻译：确定视频的特征向量
公开(公告)号：US20130113877A1
公开(公告)日：2013-05-09
申请号：US13633062
申请日：2012-10-01
申请人： RAHUL SUKTHANKAR , JAY YAGNIK
发明人： RAHUL SUKTHANKAR , JAY YAGNIK
IPC分类号： H04N13/00
CPC分类号： G06K9/00744 , G06F17/3079 , G06F17/3082 , G06K9/00718 , G06T9/00
摘要： A volume identification system identifies a set of unlabeled spatio-temporal volumes within each of a set of videos, each volume representing a distinct object or action. The volume identification system further determines, for each of the videos, a set of volume-level features characterizing the volume as a whole. In one embodiment, the features are based on a codebook and describe the temporal and spatial relationships of different codebook entries of the volume. The volume identification system uses the volume-level features, in conjunction with existing labels assigned to the videos as a whole, to label with high confidence some subset of the identified volumes, e.g., by employing consistency learning or training and application of weak volume classifiers.The labeled volumes may be used for a number of applications, such as training strong volume classifiers, improving video search (including locating individual volumes), and creating composite videos based on identified volumes.
摘要翻译：体积识别系统识别一组视频中的每一个中的一组未标记的时空体积，每个体积表示不同的对象或动作。音量识别系统进一步为每个视频确定表征整个音量的一组音量级特征。在一个实施例中，特征基于码本并且描述卷的不同码本条目的时间和空间关系。音量识别系统使用音量级特征，结合分配给整个视频的现有标签，以高度置信的方式标识所识别的体积的一些子集，例如通过采用一致性学习或训练和应用弱音量分类器。标记的卷可以用于许多应用，例如训练强大的分类器，改进视频搜索（包括定位各个卷），以及基于识别的卷创建复合视频。

3. 发明申请

US20130117780A1 VIDEO SYNTHESIS USING VIDEO VOLUMES 有权
标题翻译：视频合成使用视频卷
公开(公告)号：US20130117780A1
公开(公告)日：2013-05-09
申请号：US13633067
申请日：2012-10-01
申请人： RAHUL SUKTHANKAR , JAY YAGNIK
发明人： RAHUL SUKTHANKAR , JAY YAGNIK
IPC分类号： H04N21/236
CPC分类号： G06K9/00744 , G06F17/3079 , G06F17/3082 , G06K9/00718 , G06T9/00
摘要： A volume identification system identifies a set of unlabeled spatio-temporal volumes within each of a set of videos, each volume representing a distinct object or action. The volume identification system further determines, for each of the videos, a set of volume-level features characterizing the volume as a whole. In one embodiment, the features are based on a codebook and describe the temporal and spatial relationships of different codebook entries of the volume. The volume identification system uses the volume-level features, in conjunction with existing labels assigned to the videos as a whole, to label with high confidence some subset of the identified volumes, e.g., by employing consistency learning or training and application of weak volume classifiers. The labeled volumes may be used for a number of applications, such as training strong volume classifiers, improving video search (including locating individual volumes), and creating composite videos based on identified volumes.
摘要翻译：体积识别系统识别一组视频中的每一个中的一组未标记的时空体积，每个体积表示不同的对象或动作。音量识别系统进一步为每个视频确定表征整个音量的一组音量级特征。在一个实施例中，特征基于码本并且描述卷的不同码本条目的时间和空间关系。音量识别系统使用音量级特征，结合分配给整个视频的现有标签，以高度置信的方式标识所识别的体积的一些子集，例如通过采用一致性学习或训练和应用弱音量分类器。标记的卷可以用于许多应用，例如训练强大的分类器，改进视频搜索（包括定位各个卷），以及基于识别的卷创建复合视频。

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