一种基于本体的视频检索方法  

An Ontology-Based Video Retrieval Method

作　　者：陆琳睿[1] 周竹荣[1] 邓维[1] 

机构地区：[1]西南大学计算机与信息科学学院,重庆400715

出　　处：《西南大学学报（自然科学版）》2008年第11期119-124,共6页Journal of Southwest University(Natural Science Edition)

摘　　要：针对目前视频检索中低层特征与高层语义间存在"鸿沟"的问题,提出一种基于本体的视频检索方法,着重介绍本体框架的构造和以本体映射为核心的视频检索算法.实验结果表明该方法能够显著提高检索的查准率和查全率.Aimed at the problem of the existing gap between low-level features and high-level semantic at present, a video retrieval approach based on ontology is proposed in this paper. A detailed discussion is made of the construction of the ontology framework and the video retrieval algorithm which focus on ontology mapping. Experiment results show that this method improved markedly in terms of retrieval precision and recall rate.

关 键 词：视频本体 本体框架 视频检索 本体映射 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]