Hierarchical recognition of daily human actions based on Continuous Hidden Markov Models
Hierarchical recognition of daily human actions based on Continuous Hidden Markov Models
复制标题
DOI：
10.1109/afgr.2004.1301629
复制
发表时间：
2004-05
期刊：
影响因子：
--
通讯作者：
Taketoshi Mori;Y. Segawa;M. Shimosaka;Tomomasa Sato
中科院分区：
文献类型：
--
作者：
Taketoshi Mori;Y. Segawa;M. Shimosaka;Tomomasa Sato
本文提出了一种人体日常行为的识别方法。该方法利用层次结构的行动，并将其描述为一棵树。我们使用连续隐马尔可夫模型，它给出了一个输出的时间序列特征向量提取的特征提取过滤器的基础上人类知识的行动。该方法从根节点开始识别，然后对子节点的似然度进行竞争，选择最大似然度作为该层的识别结果，并向更深的层进行识别。分层识别的优点是：1）识别各种抽象层次，2）简化低层模型，3）通过降低细节程度来响应新数据。实验结果表明，该方法能够识别一些基本的人体动作。
This paper presents a recognition method of human daily-life action. The method utilizes hierarchical structure of actions and describes it as a tree. We model the actions by using Continuous Hidden Markov Models which gives an output of time-series feature vectors extracted by feature extraction filter based on human knowledge. In this method, recognition starts from the root, it then 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.