書誌事項
- タイトル別名
-
- Recognition of Human Daily Actions Based on Continuous Hidden Markov Models and Hierarchical Structure of Actions as Tree Representation
- カクレ マルコフ モデル ト ドウサ ノ カイソウ コウゾウ ノ モク ヒョウゲン ニ ヨル ニチジョウ ドウサ ニンシキ
この論文をさがす
抄録
This paper presents a recognition method of human daily-life action. The method utilizes hierarchical structure of actions and describes it as tree. We modelize actions by Continuous Hidden Markov Models which output time-series feature vectors extracted based on knowledge of human. In this method, recognition starts from the root, competes the likelihoods of child-nodes, chooses the maximum one as recognition result of the level, and goes to deeper level. The advantages of hierarchical recognition are: (1) recognition of various levels of abstraction, (2) simplification of low-level models, (3) response to novel data by decreasing degree of details. Experimental result shows that the method is able to recognize some basic human actions.
収録刊行物
-
- 日本ロボット学会誌
-
日本ロボット学会誌 23 (8), 957-966, 2005
一般社団法人 日本ロボット学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282679701355776
-
- NII論文ID
- 10016841684
-
- NII書誌ID
- AN00141189
-
- ISSN
- 18847145
- 02891824
-
- NDL書誌ID
- 7729349
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可