輝度勾配自己相関特徴を用いた転倒防止のための起床動作検出

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: 2014/02/01

タイトル(英語): Vision-Based Detection of Getting-up Behavior on Intensity Gradient Autocorrelation

著者名: 井上　円（名古屋工業大学），田口　亮（名古屋工業大学），梅崎　太造（名古屋工業大学）

著者名(英語): Madoka Inoue (Nagoya Institute of Technology), Ryo Taguchi (Nagoya Institute of Technology), Taizo Umezaki (Nagoya Institute of Technology)

キーワード: 行動推定，転倒防止，自己相関　　motion recognition，fall prevention，auto-correlation

要約(英語): Falls are very common among elderly patients in hospitals and nursing homes. Therefore, this paper presents recognition of getting-up motion which is an early indicator that can be used to help prevent falls. We propose a method for human action recognition based on patterns of motions. The method is constructed by autocorrelation of features extracted from edge direction and local intensity gradients. With the focus on the local regions of the image sequence, the features extracted by our proposal method are used as input information for AdaBoost. These features are turned to discriminate between different classes of action. We evaluate our algorithms on 95 video sequences, containing 31 getting-up motions and 64 different actions.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.134 No.2 （2014） 特集：知覚情報技術の最前線

本誌掲載ページ: 242-249 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/134/2/134_242/_article/-char/ja/