Structured Representation and Processing of Multi-Media Data for the Next Generation Intelligent Communication

下一代智能通信多媒体数据的结构化表示和处理

• 批准号: 04452179
• 负责人: HARASHIMA Hiroshi
• 金额: $ 4.42万
• 依托单位: The University of Tokyo
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (B)
• 财政年份: 1992
• 资助国家: 日本
• 起止时间: 1992 至 1993
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-04452179/
• 关键词: Intelligent Communication; Multi-Media; Intelligent Coding; Intelligent Human Interface; Integrated 3-D Visual Communication; Image Coding; Software Agent; Structure Recovery

This pioneering project is aiming to realize the structured representation and processing of multi-media data for the next-generation intelligent communication. The results of the project are as follows :1.Survey of the technologies related to intelligent multi-media processing.We pointed out some technological problems which must be solved for the realization of the intelligent communication system, in which the next-generation multi-media processing will play an important role. We also proposed the concept of "Integrated 3-D Visual Communication System" for the next-generation visual communication environment.Basic study on the structured representation of multi-media data.We investigated both of the 2-D and 3-D structured representation of still images and video sequences. We also proposed some methods for recovering the structural property from images, and realized real-time and quasi-real-time systems for multi-media processing.3.Basic study on combination of intelligent processing and multi-media processing.We proposed the concept of the "visual software agent" for the next-generation intelligent human interface, and investigated how to combine the intelligent processing and multi-media processing.

这一开创性的项目旨在为下一代智能通信实现多媒体数据的结构化表示和处理。本课题取得的成果如下：1.综述了智能多媒体处理的相关技术，指出了实现智能通信系统必须解决的一些技术问题，其中下一代多媒体处理将发挥重要作用。在研究多媒体数据结构化表示的基础上，对静态图像和视频序列的二维和三维结构化表示进行了研究。3.对智能处理与多媒体处理的结合进行了基础研究，提出了下一代智能人机界面的可视化软件代理的概念，并对智能处理与多媒体处理的结合进行了研究。

项目成果

苗村 健: "自己相似モデリングによる多眼三次元画像の補間と情報圧縮" テレビジョン学会誌. 48・10. 1215-1221 (1994)

Ken Naemura：“使用自相似建模的多视图 3D 图像的插值和信息压缩”电视工程师学会杂志 48・10（1994 年）。

Hiroyuki MORIKAWA: ""Incremental Segmentation of Moving Pictures-An Analysis by Synthesis Approach-"" IEICE Trans.Inf.and Syst.E76-D. 446-453 (1993)

Hiroyuki MORIKAWA：““运动图像的增量分割 - 综合方法分析 -””IEICE Trans.Inf.and Syst.E76-D。

MORIKAWA Hiroyuki: "3D Facial Modelling for Model-Based Coding" IEICE Trans.Commun.E76-B. 626-633 (1993)

MORIKAWA Hiroyuki：“基于模型编码的 3D 面部建模”IEICE Trans.Commun.E76-B。

Masahide KANEKO: ""Toward the New Era of Visual Communication"" IEICE Trans.Commun.E76-B. 577-591 (1993)

金子正秀：“迈向视觉传达的新时代”IEICE Trans.Commun.E76-B。

原島 博: "マルチメディアとその社会的課題" 情報処理学会研究報告(オーディオビジュアル複合情報処理). 1-5. 25-31 (1993)

原岛浩：“多媒体及其社会问题”日本信息处理学会研究报告（视听复杂信息处理）1-5（1993）。