| 摘要: |
| 行为识别在普适计算、人机交互等领域有着广阔的应用前景.综述了基于无线信号的行为感知与识别技术.无线行为识别具有超视距、部署简便、无需携带设备等优点.其基本思想是,传播的无线信号在人体处被阻挡、反射或散射,形成特定的传播路径.用户的不同动作使得该路径呈现不同的特点.观察无线信号在传播中的变化,就能辨识出用户的动作.介绍了无线行为识别的基本原理和应用领域,分析了该技术面临的主要挑战以及相关性能指标,并探讨了该领域的开放问题与发展趋势. |
| 关键词: 无线信号 行为识别 机器学习 动作识别 无线通信 |
| DOI： |
| 分类号: |
| 基金项目:国家自然科学基金(61070203,61472434,61202484);国家教育部博士点基金(20124307120033) |
|
| A Survey on Activity Recognition Using Wireless Signals |
|
YANG Xue, Lü Shao-He, ZHANG Min, WANG Xiao-Dong, ZHOU Xing-Ming
|
|
National Key Laboratory of Parallel and Distributed Processing, National University of Defense Technology, Changsha 410073, China
|
| Abstract: |
| Activity recognition has broad application prospects in many fields including pervasive computing and human-computer interaction. In this paper, the technology of wireless-based activity recognition is introduced. By using wireless signals, one can achieve non-line-of-sight recognition without carrying any devices. Also, it is easy to deploy a wireless-based recognition system due to the ubiquity of wireless communication system. The basic idea is that, as a specific propagation path is formed when the signal is blocked, reflected or scattered at body, one can detect the different characteristics of propagation that correspond to the distinct human behaviors. As a result, action recognition is performed by analyzing the distinguishable features of signal propagation. The basic principles and applications of wireless-based activity recognition are reviewed, and the challenges and related performance metrics are presented. Finally, open problems are discussed to point out the future research trends. |
| Key words: wireless signal activity recognition machine learning action recognition wireless communication |
