Study on intelligent video retrieval system based on semantic representation of video data

基于视频数据语义表示的智能视频检索系统研究

• 批准号: 09680398
• 负责人: UEHARA Kuniaki
• 金额: $ 1.66万
• 依托单位: Kobe University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 1997
• 资助国家: 日本
• 起止时间: 1997 至 1998
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-09680398/
• 关键词: prototype model; video database; video description model; knowledge representation; video retrieval system; 内容記述; インデックス; MOL原理; グラフマッチング; ストーリ表現

An important issue in multimedia information systems is the lack of models for semantic representation of multimedia objects to enable the search and retrieval of an appropriate multimedia object from large archives. In this research, we have studied on various aspects especially concerning video data. In our system, the typical scene is annotated by connected graph structures where graph nodes correspond to specific Affect Units. An Affect unit is an abstraction of affective causality. Our video description model is implemented based on the ideas of "object- oriented model with prototypes" which is proposed in the field of object-oriented programming. Prototype is a prefabricated object with predefined structure, contents, and behavior, from which new objects can be created by copying the prototype. By using the prototype annotation, our system enables users to create semantic representations of video content, group related sets of scene descriptors hierarchically, use these descriptors to annotate video content, and reuse descriptive effort. By using our semantic representation of video content, the database can provide the user three types of retrieval tools : keyword-based, story-based, and both-mixtured.

多媒体信息系统中的一个重要问题是缺乏多媒体对象的语义表示模型，以使搜索和检索适当的多媒体对象从大型档案。在本研究中，我们对各个方面进行了研究，特别是涉及视频数据。在我们的系统中，典型的场景是由连接的图形结构，其中图形节点对应于特定的影响单位注释。情感单位是情感因果关系的抽象。我们的视频描述模型是基于面向对象程序设计领域提出的“带原型的面向对象模型”的思想实现的。Prototype是具有预定义结构、内容和行为的预制对象，可以通过复制原型来创建新对象。通过使用原型注释，我们的系统使用户能够创建视频内容的语义表示，组相关的场景描述符集分层，使用这些描述符来注释视频内容，并重用描述性的努力。通过使用我们的视频内容的语义表示，数据库可以为用户提供三种类型的检索工具：基于关键字，基于故事，和两者混合。

项目成果

K.Zettsu: "A Time-stamped Authoring Graph for Video Scene Retrieval" Trans.of Information Processing Society of Japan. Vol.39, No.4. 923-932 (1998)

K.Zettsu：“用于视频场景检索的时间戳创作图” Trans.of 日本信息处理协会。

R.C.Paulin: "Video Summarization Based on Semantic Representation" Proc.of 1st International Conference on Advanced Multimedia Content Processing. 1-16 (1998)

R.C.Paulin：“基于语义表示的视频摘要”第一届高级多媒体内容处理国际会议论文集。

M.Kaji: "Organization by Conceptual Clustering of Video-Data based on Semantic Representation" Proc.of 5th International Conference of Foundations of Data Organization. 241-248 (1998)

M.Kaji：“基于语义表示的视频数据概念聚类组织”第五届数据组织基础国际会议论文集。

R.C.Paulin: "Video Description Model based on Prototype-Instance Model" Proc. of 6th International Conference on Database Systems for Advanced Applicatiatons. (印刷中).

R.C.Paulin：“基于原型实例模型的视频描述模型”，第六届高级应用数据库系统国际会议论文集（正在出版）。

R.C.Paulin: "Video Description Model based on Prototype-Instance Model" Proc.of 6th International Conference on Database Systems for Advanced Applications. (印刷中).

R.C.Paulin：“基于原型实例模型的视频描述模型”，第六届高级应用数据库系统国际会议论文集（正在出版）。