电子学报 ›› 2020, Vol. 48 ›› Issue (3): 602-615.DOI: 10.3969/j.issn.0372-2112.2020.03.025

• 科研通信 • 上一篇    下一篇

基于无载波超宽带雷达的小样本人体动作识别

蒋留兵1,3, 周小龙2,3, 车俐1,3   

  1. 1. 桂林电子科技大学计算机与信息安全学院, 广西桂林 541004;
    2. 桂林电子科技大学信息与通信学院, 广西桂林 541004;
    3. 桂林电子科技大学广西无线宽带通信与信号处理重点实验室, 广西桂林 541004
  • 收稿日期:2018-11-14 修回日期:2019-07-21 出版日期:2020-03-25 发布日期:2020-03-25
  • 作者简介:蒋留兵 男,1973出生,江苏泰兴人,1997年于电子科技大学获得学士学位,2006年于南京理工大学获得硕士学位,1997年至2007年在中国电子科技集团公司第十四研究所从事雷达系统的研制工作.现为桂林电子科技大学研究员,主要方向为宽带信号与信息处理、智能信息处理和人工智能在雷达系统中的应用.E-mail:jlbnj@163.com;周小龙 男,1991年出生,江西九江人,现为桂林电子科技大学硕士研究生,主要研究方向为雷达信号处理、超宽带雷达人体动作检测与识别和人工智能在雷达系统中的应用.E-mail:jeff_zhou19910914@163.com
  • 基金资助:
    国家自然科学基金项目(No.61561010);广西自然科学基金项目(No.2017GXNSFAA198089);广西重点研发计划项目(No.桂科AB18126003,No.桂科AB18221016)

Few-Shot Learning for Human Motion Recognition Based on Carrier-Free UWB Radar

JIANG Liu-bing1,3, ZHOU Xiao-long2,3, CHE Li1,3   

  1. 1. School of Computer and Information Security, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China;
    2. School of Information and Communication, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China;
    3. Key Laboratory of Wireless Broadband Communication and Signal Processing in Guangxi, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China
  • Received:2018-11-14 Revised:2019-07-21 Online:2020-03-25 Published:2020-03-25

摘要: 随着雷达硬件平台尺寸越来越小、成本越来越低,室内基于雷达的人体动作识别应用已经成为现实,能够在具有简单架构的低成本设备中实现.无载波超宽带雷达具有极高的分辨力,能够捕获人体细微动作变化并且对室内复杂环境具有很强的抗干扰能力.与基于视频人体动作识别研究相比,超宽带雷达还具有穿透家具、墙体以及保护个人隐私等优点.针对雷达回波信号利用传统时频分析方法实现人体动作识别比较耗时、实时性不好的缺陷,引入机器学习方法对不同类型人体动作进行分类识别.引入机器学习方法用于超宽带雷达人体动作识别最大难点是只有少量可用的超宽带雷达实测数据样本,针对该问题提出基于主成分分析法(PCA)和离散余弦变换(DCT)相结合的人体动作特征提取方法,并利用改进网格搜索算法优化的支持向量机在小样本数据下对人体动作进行识别,最后根据实测数据采取三种不同方案进行仿真实验,结果表明即使在训练数据样本只有5组的条件下,基于PCA和DCT相结合特征提取方法在不同类型人体动作的平均识别率均能达到96%以上.

关键词: 无载波超宽带雷达, 人体动作识别, 主成分分析法, 离散余弦变换, 小样本学习, 机器学习

Abstract: As radar hardware platforms become smaller and cheaper,indoor radar-based motion recognition applications have become reality and can be implemented in low-cost devices with simple architectures.The carrier-free ultra-wideband (UWB) radar has extremely high resolution,which can capture the slight movement of the human motion and has a strong anti-jamming capability in indoor complex environments.Human motion recognition based on UWB radar compared to video-based also has the advantage of penetrating furniture,walls and protecting personal privacy.Aiming at the defects that the traditional time-frequency analysis method based on radar realizes the human motion recognition is time-consuming and poor real-time performance,the machine learning method is introduced to classify and recognize different types of human motions.The biggest difficulty in introducing machine learning methods for UWB radar human motion recognition is that there are only a few-shot of available UWB radar measured data samples.Therefore,a human motion feature extraction method based on principal component analysis (PCA) and discrete cosine transform (DCT) is proposed.And the support vector machine (SVM) optimized by the improved grid search algorithm is used for human motion recognition under few-shot samples.Finally,simulations experiments are performed based on measured data through three different schemes.Under the condition that there are only 5 groups of training data samples,the average recognition rate of human motion recognition can reach more than 96%.

Key words: carrier-free UWB radar, human action recognition, principal component analysis (PCA), discrete cosine transform (DCT), few-shot learning, machine learning

中图分类号: