-
公开(公告)号:US08891009B2
公开(公告)日:2014-11-18
申请号:US13220000
申请日:2011-08-29
申请人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
发明人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
CPC分类号: G06K9/00751 , G06K9/4671
摘要: A system and method for retargeting video sequences are provided. A method for retargeting a video includes a plurality of frames includes determining saliency information for the plurality of frames, determining a cost metric for the video, and retargeting the video based on the cost metric to produce a retargeted video. The cost metric considers loss due to cropping, scaling, temporal factors, and spatial factors. The retargeting makes use of a crop window for each frame in the plurality of frames.
摘要翻译: 提供了一种用于重定向视频序列的系统和方法。 用于重新定位视频的方法包括多个帧包括确定多个帧的显着性信息,确定视频的成本度量,以及基于成本度量重新定位视频以产生重定向视频。 成本指标考虑到由于种植,缩放,时间因素和空间因素造成的损失。 重定向使用多个帧中的每个帧的裁剪窗口。
-
公开(公告)号:US20120033949A1
公开(公告)日:2012-02-09
申请号:US13103810
申请日:2011-05-09
申请人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
发明人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
IPC分类号: G11B27/00
CPC分类号: G11B27/031 , G06K9/00751 , G11B27/034 , G11B27/28
摘要: In an embodiment, a method of creating a skimming preview of a video includes electronically receiving a plurality of video shots, analyzing each frame in a video shot from the plurality of video shots, where analyzing includes determining a saliency of each frame of the video shot. The method also includes determining a key frame of the video shot based on the saliency of each frame the video shot, extracting visual features from the key frame, performing shot clustering of the plurality of video shots to determine concept patterns based on the visual features, and generating a reconstruction reference tree based on the shot clustering. The reconstruction reference tree includes video shots categorized according to each concept pattern.
摘要翻译: 在一个实施例中,创建视频的撇取预览的方法包括电子地接收多个视频镜头,分析来自多个视频镜头的视频拍摄中的每个帧,其中分析包括确定视频拍摄的每个帧的显着性 。 该方法还包括基于视频拍摄的每帧的显着性来确定视频镜头的关键帧,从关键帧提取视觉特征,执行多个视频镜头的拍摄聚类,以基于视觉特征来确定概念模式, 以及基于所述拍摄聚类生成重建参考树。 重建参考树包括根据每个概念模式分类的视频镜头。
-
公开(公告)号:US09171578B2
公开(公告)日:2015-10-27
申请号:US13103810
申请日:2011-05-09
申请人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
发明人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
IPC分类号: G06K9/62 , G11B27/034 , G11B27/28
CPC分类号: G11B27/031 , G06K9/00751 , G11B27/034 , G11B27/28
摘要: In an embodiment, a method of creating a skimming preview of a video includes electronically receiving a plurality of video shots, analyzing each frame in a video shot from the plurality of video shots, where analyzing includes determining a saliency of each frame of the video shot. The method also includes determining a key frame of the video shot based on the saliency of each frame the video shot, extracting visual features from the key frame, performing shot clustering of the plurality of video shots to determine concept patterns based on the visual features, and generating a reconstruction reference tree based on the shot clustering. The reconstruction reference tree includes video shots categorized according to each concept pattern.
摘要翻译: 在一个实施例中,创建视频的撇取预览的方法包括电子地接收多个视频镜头,分析来自多个视频镜头的视频拍摄中的每个帧,其中分析包括确定视频拍摄的每个帧的显着性 。 该方法还包括基于视频拍摄的每帧的显着性来确定视频镜头的关键帧,从关键帧提取视觉特征,执行多个视频镜头的拍摄聚类,以基于视觉特征来确定概念模式, 以及基于所述拍摄聚类生成重建参考树。 重建参考树包括根据每个概念模式分类的视频镜头。
-
公开(公告)号:US20130050574A1
公开(公告)日:2013-02-28
申请号:US13220000
申请日:2011-08-29
申请人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
发明人: Taoran Lu , Zheng Yuan , Yu Huang , Dapeng Oliver Wu , Hong Heather Yu
IPC分类号: H04N7/01
CPC分类号: G06K9/00751 , G06K9/4671
摘要: A system and method for retargeting video sequences are provided. A method for retargeting a video includes a plurality of frames includes determining saliency information for the plurality of frames, determining a cost metric for the video, and retargeting the video based on the cost metric to produce a retargeted video. The cost metric considers loss due to cropping, scaling, temporal factors, and spatial factors. The retargeting makes use of a crop window for each frame in the plurality of frames.
摘要翻译: 提供了一种用于重定向视频序列的系统和方法。 用于重新定位视频的方法包括多个帧包括确定多个帧的显着性信息,确定视频的成本度量,以及基于成本度量重新定位视频以产生重定向视频。 成本指标考虑到由于种植,缩放,时间因素和空间因素造成的损失。 重定向使用多个帧中的每个帧的裁剪窗口。
-
-
-