ロボット聴覚とプラン認識に基づく環境理解のためのPlan-Intention-Eventフレームワーク

Material type: 博士論文

Author: 小島, 諒介ほか

Publisher: -

Publication date: 2017-03

Material Format: Digital

Capacity, size, etc.: -

Name of awarding university/degree: 東京工業大学,博士(工学)

View All

Notes on use

Note (General)：: This thesis addresses scene analysis, which is essential for environmental monitoring and understanding. The main problems for scene analysis are twof...

Search by Bookstore

Holdings of Libraries in Japan

This page shows libraries in Japan other than the National Diet Library that hold the material.

List of Cooperating Institutions and Databases

Please contact your local library for information on how to use materials or whether it is possible to request materials from the holding libraries.

other

Tokyo Tech Research Repository
Digital
You can check the holdings of institutions and databases with which 学術機関リポジトリデータベース（IRDB）（機関リポジトリ） is linked at the site of 学術機関リポジトリデータベース（IRDB）（機関リポジトリ）.
Tokyo Tech Research Repository

Search by Bookstore

Bibliographic Record

You can check the details of this material, its authority (keywords that refer to materials on the same subject, author's name, etc.), etc.

Digital

Material Type: 博士論文
Title: ロボット聴覚とプラン認識に基づく環境理解のためのPlan-Intention-Eventフレームワーク
Author/Editor: 小島, 諒介
Kojima, Ryosuke
Author Heading: 小島, 諒介
Kojima, Ryosuke
Publication Date: 2017-03
Publication Date (W3CDTF): 2017-03
Alternative Title: Plan-Intention-Event Framework for Scene Analysis Based on Robot Audition and Plan Recognition
Degree grantor/type: 東京工業大学
Date Granted: 2017-03-26
Dissertation Number: 甲第10554号
Degree Type: 博士(工学)
Text Language Code: eng
Subject Heading: 環境理解
Scene analysis
ロボット聴覚
robot audition
プラン認識
plan recognition
Target Audience: 一般
Note (General): This thesis addresses scene analysis, which is essential for environmental monitoring and understanding. The main problems for scene analysis are twofold; extraction of attributes and reconstruction of scene structure from signal data obtained from sensors. To resolve them, we propose a scene analysis framework by combining unified event extraction and stochastic plan recognition. Unified event extraction considers the probabilistic relationship between attributes of a scene event to extract attributes more accurately than conventional methods dealing with attributes separately. Stochastic plan recognition structures the extracted events with back-ground knowledge, which yields plausible reconstruction of scene structure. This thesis also shows effectiveness of the proposed framework by introducing three applications: cooking recognition, bird song analysis, and web session log monitoring.
identifier:oai:t2r2.star.titech.ac.jp:50359915
Format (IMT): application/pdf
Source: http://t2r2.star.titech.ac.jp/rrws/file/CTT100736587/ATD100000413/Main.pdf （fulltext）
http://t2r2.star.titech.ac.jp/rrws/file/CTT100736587/ATD100000413/Main.pdf
Access Restrictions: インターネット公開
Data Provider (Database): 国立情報学研究所 : 学術機関リポジトリデータベース（IRDB）（機関リポジトリ）
https://irdb.nii.ac.jp
Original Data Provider (Database): 東京工業大学 : 東京工業大学リサーチリポジトリ