精密工学会誌
Online ISSN : 1882-675X
Print ISSN : 0912-0289
ISSN-L : 0912-0289
画像技術の実利用特集論文
行動遷移映像における姿勢特徴を中心とする学習を用いた時系列行動認識
鈴木 智之青木 義満
著者情報
ジャーナル フリー

2017 年 83 巻 12 号 p. 1156-1165

詳細
抄録

In this paper, we propose a method of human action recognition for videos in which actions are continuously transitioning. First, we make pose estimator which has learned joint coordinates using Convolutional Neural Networks (CNN) and extract feature from intermediate structure of it. Second, we train action recognizer structured by Long Short-Term Memory (LSTM), using pose feature and environmental feature as inputs. At that time, we propose Pose-Centric Learning. In addition, from pose feature we calculate Attention that represents importance of environmental feature for each element, and filtering latter feature by Attention to make this effective one. When modeling action recognizer, we structure Hierarchical model of LSTM. In experiments, we evaluated our method comparing to conventional method and achieve 15.7% improvement from it on challenging action recognition dataset.

著者関連情報
© 2017 公益社団法人 精密工学会
前の記事 次の記事
feedback
Top