摘要
视频摘要能够充分表达视频信息.在MPEG-1/2中,关键帧可以反映镜头的内容.类似地,关键视频对象可以表示基于MPEG-4对象框架的视频内容.将关键视频对象选择模型(key video object selection model,简称KVOS)扩展为基于交互计算的交互式关键视频对象选择模型(interactive key video object selection model,简称IKVOS),并证明了关键视频对象选择模型满足归纳法准则,交互式关键视频对象选择模型满足余归纳法准则.同时用户可以根据偏好灵活选取关键视频对象.实验表明,根据紧凑和全面策略选择的关键视频对象,其失真率均低于相关方法.
Summarization of video can well represent the content of video. In the MPEG-1/2 standard key frame is used for representing the content of a video sequence. Similarly, in an object-based framework of the suggested MPEG-4 standard, key video object can summarize the content of video objects. In this paper, an interactive key video objects selection model （IKVOS） is presented as the result of improving the model of key video objects selection （KVOS）. The model of KVOS is proved to satisfy the criterion of induction. Also, the course of IKVOS is formalized and the model of IKVOS is proved to satisfy the criterion of coinduction. It can dynamically generate key video objects with user＇s preference. The experimental results are given, as well as the evaluation of the performance of the proposed method whose distortion rate is lower than the current methods.
出处
《软件学报》
EI
CSCD
北大核心
2007年第3期547-554,共8页
Journal of Software
基金
Supported by the National Natural Science Foundation of China under Grant No.60473002(国家自然科学基金)
the Key Project of Beijing Natural Science Foundation of China under Grant No.4051004(北京市自然基金重点项目)
the Scientific Research Fund of Hu’nan Provincial Education Department of China under Grant No.06B095 (湖南省教育厅科研项目)
