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

US20130259390A1 Systems and Methods for Semantically Classifying and Normalizing Shots in Video 有权
标题翻译：视频中语义分类和归一化镜头的系统和方法
公开(公告)号：US20130259390A1
公开(公告)日：2013-10-03
申请号：US13438435
申请日：2012-04-03
申请人： Heather Dunlop , Matthew Berry
发明人： Heather Dunlop , Matthew Berry
IPC分类号： G06K9/62
CPC分类号： G06K9/00718 , G06K9/00751 , G06K9/52 , G06K9/6215 , G06T7/174 , G06T2207/10016 , G06T2207/20021
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

2. 发明授权

US09020263B2 Systems and methods for semantically classifying and extracting shots in video 有权
标题翻译：视频中语义分类和提取镜头的系统和方法
公开(公告)号：US09020263B2
公开(公告)日：2015-04-28
申请号：US13438395
申请日：2012-04-03
申请人： Heather Dunlop , Matthew Berry
发明人： Heather Dunlop , Matthew Berry
IPC分类号： G06K9/34 , G06K9/62 , G06K9/00 , G06K9/03 , G06K9/46
CPC分类号： G06K9/00684 , G06K9/00697 , G06K9/00718 , G06K9/00744 , G06K9/036 , G06K9/4676
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

3. 发明申请

US20140321746A9 Systems and Methods for Semantically Classifying and Extracting Shots in Video 有权
标题翻译：视频中语义分类和提取镜头的系统和方法
公开(公告)号：US20140321746A9
公开(公告)日：2014-10-30
申请号：US13438395
申请日：2012-04-03
申请人： Heather Dunlop , Matthew Berry
发明人： Heather Dunlop , Matthew Berry
IPC分类号： G06K9/62 , G06K9/34
CPC分类号： G06K9/00684 , G06K9/00697 , G06K9/00718 , G06K9/00744 , G06K9/036 , G06K9/4676
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

4. 发明申请

US20090208106A1 SYSTEMS AND METHODS FOR SEMANTICALLY CLASSIFYING SHOTS IN VIDEO 有权
标题翻译：在视频中进行分类分类的系统和方法
公开(公告)号：US20090208106A1
公开(公告)日：2009-08-20
申请号：US12372561
申请日：2009-02-17
申请人： Heather Dunlop , Matthew G. Berry
发明人： Heather Dunlop , Matthew G. Berry
IPC分类号： G06K9/34 , G06K9/62
CPC分类号： G06K9/00664 , G06K9/00711
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

5. 发明授权

US08311344B2 Systems and methods for semantically classifying shots in video 有权
标题翻译：视频中镜像语义分类的系统和方法
公开(公告)号：US08311344B2
公开(公告)日：2012-11-13
申请号：US12372561
申请日：2009-02-17
申请人： Heather Dunlop , Matthew G. Berry
发明人： Heather Dunlop , Matthew G. Berry
IPC分类号： G06K9/62
CPC分类号： G06K9/00664 , G06K9/00711
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

6. 发明授权

US09111146B2 Systems and methods for semantically classifying and normalizing shots in video 有权
标题翻译：在视频中语义分类和归一化镜头的系统和方法
公开(公告)号：US09111146B2
公开(公告)日：2015-08-18
申请号：US13438435
申请日：2012-04-03
申请人： Heather Dunlop , Matthew Berry
发明人： Heather Dunlop , Matthew Berry
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00718 , G06K9/00751 , G06K9/52 , G06K9/6215 , G06T7/174 , G06T2207/10016 , G06T2207/20021
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

7. 发明申请

US20130259375A1 Systems and Methods for Semantically Classifying and Extracting Shots in Video 有权
标题翻译：视频中语义分类和提取镜头的系统和方法
公开(公告)号：US20130259375A1
公开(公告)日：2013-10-03
申请号：US13438395
申请日：2012-04-03
申请人： Heather Dunlop , Matthew Berry
发明人： Heather Dunlop , Matthew Berry
IPC分类号： G06K9/62 , G06K9/34
CPC分类号： G06K9/00684 , G06K9/00697 , G06K9/00718 , G06K9/00744 , G06K9/036 , G06K9/4676
摘要： The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.
摘要翻译：本公开涉及基于视频内容对视频进行分类的系统和方法。对于包括多个帧的给定视频文件，提取帧的子集用于处理。从子集中丢弃太暗，模糊或其他不良分类候选的帧。通常，针对子集中的剩余帧计算描述每帧中可能包括的材料内容类型的材料分类分数。材料分类分数用于生成表示每帧中材料内容的空间排列的材料排列向量。随后将材料排列向量分类以产生每帧的场景分类分数向量。场景分类结果在子集中的所有帧上被平均（或以其它方式处理），以将视频文件与与视频文件的场景内容的总体类型相关的一个或多个预定义场景类别相关联。

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