| 本文已被：浏览 5172次 下载 5943次 |
码上扫一扫！ |
|
|
| 交互式关键视频对象选择模型 |
|
欧阳建权1,2,3, 李锦涛1, 张勇东1
|
|
1.中国科学院,计算技术研究所,北京,100080;2.湘潭大学,信息工程学院,湖南,湘潭,411105;3.中国科学院,研究生院,北京,100049
|
|
| 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 |
| 关键词: 关键视频对象 交互式关键视频对象选择 交互计算 归纳法 余归纳法 |
| DOI： |
| 分类号: |
| 基金项目: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 |
|
| An Interactive Key Video Object Selection Model |
|
OUYANG Jian-Quan,LI Jin-Tao,ZHANG Yong-Dong
|
| Abstract: |
| 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. |
| Key words: key video object interactive key video object selection interactive computing induction coinduction |
