Teaching Assistant System used Eye Tracking Device Based on Gaze Estimation by Neural Network and Intention Recognition by Fuzzy Inference

Material type: 文書・図像類

Author: Wang, Maoほか

Publisher: International Information Institute

Publication date: 2014-09

Material Format: Digital

Capacity, size, etc.: -

NDC: -

View All

Notes on use

Note (General)：: Intention recognition can use multiple factors as inputs such as gestures, face images and eye gaze position. On the other hand,eye tracking technolog...

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

Ｕｎｉｖｅｒｓｉｔｙ　ｏｆ　Ｆｕｋｕｉ　Ａｃａｄｅｍｉｃ　Ｒｅｐｏｓｉｔｏｒｙ
Digital
You can check the holdings of institutions and databases with which Institutional Repositories DataBase(IRDB)(Institutional Repository) is linked at the site of Institutional Repositories DataBase(IRDB)(Institutional Repository).
Ｕｎｉｖｅｒｓｉｔｙ　ｏｆ　Ｆｕｋｕｉ　Ａｃａｄｅｍｉｃ　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: 文書・図像類
Title: Teaching Assistant System used Eye Tracking Device Based on Gaze Estimation by Neural Network and Intention Recognition by Fuzzy Inference
Author/Editor: Wang, Mao
Maeda, Yoichiro
Takahashi, Yasutake
Author Heading: Wang, Mao
Maeda, Yoichiro
Takahashi, Yasutake
Publication, Distribution, etc.: International Information Institute
Publication Date: 2014-09
Publication Date (W3CDTF): 2014-09
Periodical title: Information
No. or year of volume/issue: 17 9(B)
Volume: 17
Issue: 9(B)
Pages: 4661-4676
ISSN (Periodical Title): ISSN : 1343-4500
Text Language Code: eng
Subject Heading: Eye Tracking
Neural Network
Intention Recognition
Fuzzy Inference
Humanoid Robot
Target Audience: 一般
Note (General): Intention recognition can use multiple factors as inputs such as gestures, face images and eye gaze position. On the other hand,eye tracking technology,with its special advantages of applying to Human-Computer Interaction (HCI),can be utilized to develop assistant systems for people with mobility difficulties. In this paper, we propose gaze estimation position information as input of fuzzy inference to achieve intention recognition based on object recongition and construct an assistant system by using humanoid robot. Our approach is divided into three parts: user's gaze estimation, intention recognition and behavior execution. In gaze estimation part, differing from the previous studies, neural network has been used as the decision making unit, and then gaze position on computer screen is estimated. In intention recognition part, user intention is recognized by using gaze frequency and continuous gaze staying time as input of fuzzy inference after an initial intention region set has been found. At last, by using an autonomous humanoid robot, experiments are performed based on the result of intention recognition. after confirmed by user, the robot was controlled with and assistant task for user precisely.
Access Restrictions: 限定公開
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): 福井大学 : 福井大学学術機関リポジトリ