发明申请
US20130251274A1 LIMITED-CONTEXT-BASED IDENTIFYING KEY FRAME FROM VIDEO SEQUENCE
有权
有限的基于语境的识别关键帧从视频序列
- 专利标题: LIMITED-CONTEXT-BASED IDENTIFYING KEY FRAME FROM VIDEO SEQUENCE
- 专利标题(中): 有限的基于语境的识别关键帧从视频序列
-
申请号: US13991721申请日: 2010-12-09
-
公开(公告)号: US20130251274A1公开(公告)日: 2013-09-26
- 发明人: Xiaohui Xie , Xiao Zeng , Yingfei Liu , Yanming Zou , Kongqiao Wang , Zhicheng Zhao , Anni Cai
- 申请人: Xiaohui Xie , Xiao Zeng , Yingfei Liu , Yanming Zou , Kongqiao Wang , Zhicheng Zhao , Anni Cai
- 申请人地址: FI Espoo
- 专利权人: NOKIA CORPORATION
- 当前专利权人: NOKIA CORPORATION
- 当前专利权人地址: FI Espoo
- 国际申请: PCT/CN10/79601 WO 20101209
- 主分类号: G06K9/62
- IPC分类号: G06K9/62
摘要:
An example apparatus is caused to receive a video sequence of a plurality of frames, and perform a number of operations as each of at least some of the frames is received but before all of the frames are received. The apparatus is caused to calculate a score for the frame, and compare the score for the frame to a predefined threshold. The apparatus is caused to cause output of the frame as a key frame in an instance in which the frame is received within a specified period of time and the score for the frame is above the predefined threshold. Otherwise, in an instance in which none of the scores for frames received within the specified period of time is above the predefined threshold, the apparatus is caused to cause output of one of the frames received within the specified period of time as a key frame.
公开/授权文献
信息查询