基于格框架的视频事件时空相关描述分析方法

系统仿真学报 ›› 2015, Vol. 27 ›› Issue (4): 770-778.

基于格框架的视频事件时空相关描述分析方法

柯佳^1,2, 詹永照², 陈潇君³, 汪满容⁴

1.江苏大学管理学院, 镇江市 212013;
2.江苏大学计算机学院, 镇江市 212013;
3.江苏大学附属医院信息科, 镇江市 212013;
4.江苏大学图书馆, 镇江市 212013

收稿日期:2014-02-18 修回日期:2014-04-11 发布日期:2020-08-20
作者简介:柯佳(通信作者1981-),女,江苏,博士,讲师,研究方向为多媒体技术;詹永照(1962-),男,福建,博士,教授,研究方向为多媒体技术、模式识别;陈潇君(1981-),男,上海,硕士,工程师,研究方向为多媒体技术。
基金资助:
国家自然科学基金资助项目(61170126);国家自然科学基金青年科学基金项目(61203244);江苏大学高级技术人才科研启动基金项目(13JDG126)

Spatio-temporal Correlation Described and Analysis Method of Video Event Based on Case Frame

Ke Jia^1,2, Zhan Yongzhao², Chen Xiaojun³, Wang Manrong⁴

1. School of Management, Jiangsu University, Zhenjiang 212013, China;
2. School of Computer Science and Telecommunication Engineering, Jiangsu University, Zhenjiang 212013, China;
3. Affiliated Hospital of Jiangsu University, Zhenjiang 212013, China;
4. Jiangsu University Library, Zhenjiang 212013, China

Received:2014-02-18 Revised:2014-04-11 Published:2020-08-20

摘要/Abstract

摘要： 在海量的视频资源中,如何描述和表示视频事件内容,是当下多媒体信息处理的热点问题之一。在用于自然语言理解的格语法理论基础上,引入了语义框架结构,设计了用以描述复杂事件中的子事件之间关系的格框架结构,并定义了视频综合事件中子事件框架关系。其中,在子事件参照关联关系上,对子事件的时间、空间关联性进行了分析推理。并采用格语义框架网络(Case Semantic Frame Net, CSFN)对实际监控视频集中的典型事件进行描述和时空关联分析,对比了格框架网络和传统格语法方法对事件进行描述分析之后,用户对视频进行检索的结果。实验证明,格框架网络能更加准确地描述和理解复杂事件,并有效提高视频事件检索的准确率和召回率。

关键词: 格语法, 格框架, 复杂事件, 子事件, 参照完整性

Abstract: In the mass of video resources, how to describe and represent video event content is one of hot issues in the current multimedia information processing. The original theory of case grammar for natural language understanding was extended; Case Frame was designed to describe the relationships between the structures of complex events in the sub-events. In Ref_Asso, which is one of relationships, spatio-temporal correlation was analyzed and reasoned among sub-events. In the experimental part, Case Semantic Frame Net was used to describe and understand the typical complex events in surveillance video. And results of users' retrieval were compared; in which video test set was described respectively with Case Semantic Frame Net and traditional Case grammar. Experiment results show that the new method can more accurately describe and understand complex events, and has a higher precision and recall rate in video retrieval.

Key words: case grammar, case framework, complex events, sub-event, Ref_Asso

中图分类号:

TP391.9

柯佳, 詹永照, 陈潇君, 汪满容. 基于格框架的视频事件时空相关描述分析方法[J]. 系统仿真学报, 2015, 27(4): 770-778.

Ke Jia, Zhan Yongzhao, Chen Xiaojun, Wang Manrong. Spatio-temporal Correlation Described and Analysis Method of Video Event Based on Case Frame[J]. Journal of System Simulation, 2015, 27(4): 770-778.