期刊
NEUROCOMPUTING
卷 175, 期 -, 页码 747-758出版社
ELSEVIER
DOI: 10.1016/j.neucom.2015.11.005
关键词
Activity recognition; Bag-of-Visual-Words; Depth data; Shape context
资金
- National Natural Science Foundation of China (NSFC) [61340046]
- National High Technology Research and Development Programme of China (863 Programme) [2006AA04Z247]
- Scientific and Technical Innovation Commission of Shenzhen Municipality [JCYJ20120614152234873, JCYJ20130331144716089]
- Specialized Research Fund for the Doctoral Programme of Higher Education (SRFDP) [20130001110011]
Human activity recognition using sole depth information from 3D sensors achieves superior performances to tackle light changes and cluttered backgrounds than using RGB sequences from traditional cameras. However, the noises and occlusions in depth data, which are common problems for 3D sensors, are not well handled. Moreover, many existing methods ignore the strong contextual information from depth data, resulting in limited performances on distinguishing similar activities. To deal with these problems, a local point detector is developed by sampling local points based on both motion and shape clues to represent human activities in depth sequences. Then a novel descriptor named Depth Context is designed for each local point to capture both local and global contextual constrains. Finally, a Bag-of-Visual-Words (BoVW) model is applied to generating human activity representations, which serve as the inputs for a non-linear SVM classifier. State-of-the-art results namely 94.28%, 98.21% and 95.37% are achieved on three public benchmark datasets: MSRAction3D, MSRGesture3D and SIGG, which show the efficiency of proposed method to capture structural depth information. Additional experimental results show that our method is robust to partial occlusions in depth data, and also robust to the changes of pose, illumination and background to some extent. (C) 2015 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据