A research into advanced and high-speed multi-media understanding based on a parallel processing model

基于并行处理模型的先进高速多媒体理解研究

• 批准号: 05680300
• 负责人: TANIGUCHI Rinichiro
• 金额: $ 1.28万
• 依托单位: KYUSHU UNIVERSITY
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for General Scientific Research (C)
• 财政年份: 1993
• 资助国家: 日本
• 起止时间: 1993 至 1994
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-05680300/
• 关键词: Multi-media; Parallel processing system; Parallel programming language; Parallel processor architecture; Model acquisition; Integration of signal and symbolic computation; 映像信号処理; 並列処理モデル; マンマシンインターフェース; 信号と記号; 並列処理プログラミング; 画像理解; 情報の統合化; マルチエ

(1)Integration of signal processing and symblic processingWe have investigated an interface mechanism between pattern information and symbolic information, which are quite important in multi-media processing, and proposed a framework of cooperative processing of top-down and bottom-up processing.(2)Programming for parallel processing of multi-media understandingIn a parallel multi-media understanding system, the idea of a multi-agent system, in which various processing modules operate cooperatively, is quite important. According to this consideration, we have designed a programming language for multi-agent systems, which supports parallel object-oriented computation.(3)Parallel architecture for multi-media understandingwe have designed a basic architecture of a multi-media oriented parallel processor, called KUMP/D (the Kyushu University Multi-media Processor on Datarol-II). In this project, we have establishedaspecialized parallel I/O interfacefor a real-time video, which realizessynchronization among real-time videosignals and processor elements.(4)Automatic model generation from pictorial examples,As a framework of automatic model generation for pictorial pattern recognition, we have developed a mechanism, which generates a model of a class of objects based on two dimensional features derived from a set of image examples. The model is represented in a segmentation tree representing a hierarchical structure of image regions and having various features of the regions.

（1）信号处理与符号处理的集成研究了多媒体处理中的模式信息与符号信息之间的接口机制，提出了自顶向下与自底向上的协同处理框架。（2）多媒体理解的并行处理程序设计在并行多媒体理解系统中，多个处理模块协同工作的多智能体系统的思想是非常重要的。根据这一考虑，我们设计了一个多智能体系统的编程语言，它支持并行面向对象的计算。（3）面向多媒体理解的并行结构我们设计了一个面向多媒体的并行处理器KUMP/D（the Kyushu University Multi-media Processor on Datarol-Ⅱ）的基本结构。在本项目中，我们为实时视频建立了专用的并行I/O接口，实现了实时视频信号和处理器单元之间的同步。（4）基于图像样本的模型自动生成作为图像模式识别模型自动生成的框架，我们开发了一种基于图像样本的二维特征生成一类对象模型的机制。该模型被表示在表示图像区域的分层结构并且具有区域的各种特征的分割树中。

项目成果

Hiroshi Tomiyasu, Tetsuo Kawano, Rin-ichiro Taniguchi and Makoto Amamiya: ""Fine grain multi-thread processing in Datarol-II processor element using a off-the-shelf micro processor"" Engineering Sciences Reports, Kyushu University. Vol.16, No.3. 331-338 (

Hiroshi Tomiyasu、Tetsuo Kawano、Rin-ichiro Taniguchi 和 Makoto Amamiya：“使用现成的微处理器在 Datarol-II 处理器元件中进行细粒度多线程处理”，九州大学工程科学报告。

Rin-ichiro Taniguchi: ""Software architecture for parallel computer vision"" Journal of Japanese Society for Artificial Intelligence. Vol.9, No.5. 652-658 (1994)

Rin-ichiro Taniguchi：“并行计算机视觉的软件架构”，日本人工智能学会杂志。

赤木琢磨 中村明憲 鶴田直之 谷口倫一郎 雨宮真人: "自律分散モデルに基づく対話型画像理解システム" 第5回自律分散システム・シンポジウム. 1. 149-154 (1994)

Takuma Akagi、Akinori Nakamura、Naoyuki Tsuruta、Rinichiro Taniguchi、Masato Amemiya：“基于自治分布式模型的交互式图像理解系统”第 5 届自治分布式系统研讨会 1. 149-154 (1994)。

谷口 倫一郎 日下部 茂 雨宮 真人: "超並列処理記述言語Vによる画像処理アルゴリズムの記述" 情報処理学会研究報告パターン認識・理解研究会. 1. 81-88 (1993)

Rinichiro Taniguchi、Shigeru Kusakabe 和 Masato Amemiya：“使用大规模并行处理描述语言 V 的图像处理算法的描述”日本信息处理学会研究报告模式识别和理解研究组 1. 81-88 (1993)。

Noriyasu Yamamoto, Naoyuki Tsuruta, Rin-ichiro Taniguchi and Makoto Amamiya: ""Massively Parallel Image Processing on AMP (Autonomous Multi Processor)"" Proc.of Asian Conf.on computer Vision '93. 705-709 (1993)

Noriyasu Yamamoto、Naoyuki Tsuruta、Rin-ichiro Taniguchi 和 Makoto Amamiya：“AMP（自主多处理器）上的大规模并行图像处理”Proc.of Asian Conf.on Computer Vision 93。