統計的相関を用いて運動と言語の構造を結びつけたデータベースの設計

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2013/09/01

タイトル(英語): Design of Motion Database with Language by Using Stochastic Correlation

著者名: 高野　渉（東京大学　情報理工学系研究科），濱野　聖也（東京大学　情報理工学系研究科），中村　仁彦（東京大学　情報理工学系研究科）

著者名(英語): Wataru Takano (Graduate School of Information Science and Technology, The University of Tokyo), Seiya Hamano (Graduate School of Information Science and Technology, The University of Tokyo), Yoshihiko Nakamura (Graduate School of Information Science and Technology, The University of Tokyo)

キーワード: 運動の記号化，言語，正準相関分析，運動データベース　　Symbolization of motion，language，canonical correlation analysis，motion database

要約(英語): The motion capture systems have been improved, and widely used for motion analysis and synthesis in fields of robotics, animation, rehabilitation, and sports engineering. A lot of captured human data have been accumulated. These prerecorded motion data are expected to be reused. The retrieval of a specified motion data is a fundamental technique for the reuse. This paper describes a novel approach to retrieve motion data from word queries out of a large motion dataset. The motion data are trained by Hidden Markov Models, each of which symbolizes a motion pattern. The motion data are also manually given word labels. The mapping between motion symbols and word labels are optimized through canonical correlation analysis so that correlation between them can be maximized. This mapping makes it possible to project a word query to motion features, and to search for motions similar to the motion features. The validity of the proposed approach was demonstrated on captured motion data.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.133 No.9 （2013） 特集：エージェントシミュレーションの最新動向

本誌掲載ページ: 1680-1686 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/133/9/133_1680/_article/-char/ja/