Abstract: The approach based on the local spatial-temporal features has emerged to be the mainstream method in action recognition area. And various descriptors of local spatial-temporal feature have been presented by researchers. However, different local features may reflect different emphasis of human activity. In this paper, the ensemble learning methods are introduced to perform a late fusion of multiple features so as to enhance the expressing ability of the local features. By the fusion of features, a more effective and robust action classifier can be built up. And the  experimental results demonstrate the robustness and effectiveness of the proposed method.

Key words: ensemble learning, multi-feature fusion, action recognition

摘要： 基于时空特征的方法是行为识别的主流方法，已经有许多研究学者提出了多种局部时空特征。然而，不同的局部特征所反映的行为信息的侧重点并不一样。通过引入集成学习的方法，对多种特征在分类器层次上进行融合，使得多种特征能够优势互补，从而增强了特征的描述能力，为构建出高效、稳定的行为识别分类器提供了保证。经仿真实验验证，所提出的方法是鲁棒和有效的。

关键词: 集成学习, 多特征融合, 行为识别