| 引用本文: | 白亮,老松杨,侯小强,等.一个知识辅助的视频语义概念探测框架.[J].国防科技大学学报,2012,34(4):90-94.[点击复制] |
| BAI Liang,LAO Songyang,HOU Xiaoqiang,et al.A knowledge-assisted framework for video semantic concept detection[J].Journal of National University of Defense Technology,2012,34(4):90-94[点击复制] |
|
| |
|
|
| 本文已被：浏览 10014次 下载 7261次 |
| 一个知识辅助的视频语义概念探测框架 |
| 白亮1, 老松杨1, 侯小强2, 刘海涛1, 卜江1 |
|
(1.国防科技大学 信息系统工程重点实验室，湖南 长沙 410073;2.61046部队,北京 100094)
|
| 摘要: |
| 视频语义概念探测是视频语义内容分析研究领域的热点和难点问题。语义概念探测方法的性能取决于其是否能够有效地建模和匹配视频语义内容特征。将视频内容抽象为感知概念和语义概念以及概念间的关系，提出了知识辅助的视频语义概念探测框架，利用本体建模概念间关系和上下文知识，从低层特征匹配和上下文匹配两个方面综合考虑语义概念的探测。通过线性融和策略，对匹配结果进行融合得到最终的探测结果。实验结果表明提出的方法探测性能良好。 |
| 关键词: 本体 视频语义概念探测 上下文信息 低层特征 |
| DOI： |
| 投稿日期：2011-12-20 |
| 基金项目:国家自然科学青年基金项目（60902094）;“十二五”国家部委项目 |
|
| A knowledge-assisted framework for video semantic concept detection |
| BAI Liang1, LAO Songyang1, HOU Xiaoqiang2, LIU Haitao1, BU Jiang1 |
|
(1.Science and Technology on Information System Engineering, National University of Defense Technology, Changsha 410073, China;2.PLA Unit 61046 Beijing 100094, China)
|
| Abstract: |
| Semantic concept detection in video is a challenge for video semantic content analysis. The performance of semantic concept detection methods depends on modeling and matching the video semantic content exactly. In this research, perception concept and semantic concept were defined to abstract and model video semantic content. Furthermore, the knowledge-assisted framework for semantic concept detection was proposed, in which the context knowledge was modeled using ontology, and the semantic concepts were detected by combining with low-level features and context information. Finally, the linear fusion strategy was used to fuse the matching results and detect the semantic concepts. The proposed method was demonstrated in a news video domain and shows promising results. |
| Keywords: knowledge-assisted ontology video semantic concept detection context |
|
|
|
|
|
