Dynamic action recognition based on dynemes and Extreme Learning Machine
详细信息 查看全文
- 作者：Alex ; ros Iosifidis ; Anastasios Tefas ; Ioannis Pitas
- 关键词：Activity recognition ; Dynamic classification ; Fuzzy vector quantization ; Extreme Learning Machine
- 刊名：Pattern Recognition Letters
- 出版年：2013
- 出版时间：1 November, 2013
- 年：2013
- 卷：34
- 期：15
- 页码：1890-1898
- 全文大小：1994 K
文摘
In this paper, we propose a novel method that performs dynamic action classification by exploiting the effectiveness of the Extreme Learning Machine (ELM) algorithm for single hidden layer feedforward neural networks training. It involves data grouping and ELM based data projection in multiple levels. Given a test action instance, a neural network is trained by using labeled action instances forming the groups that reside to the test sample¡¯s neighborhood. The action instances involved in this procedure are, subsequently, mapped to a new feature space, determined by the trained network outputs. This procedure is performed multiple times, which are determined by the test action instance at hand, until only a single class is retained. Experimental results denote the effectiveness of the dynamic classification approach, compared to the static one, as well as the effectiveness of the ELM in the proposed dynamic classification setting.