Human motion recognition exploiting radar with stacked recurrent neural network

被引：93

作者：

Wang, Mingyang ^{[1
]}

Zhang, Yimin D. ^{[2
]}

Cui, Guolong ^{[1
]}

机构：

[1] Univ Elect Sci & Technol China, Sch Informat & Commun Engn, Chengdu 611731, Sichuan, Peoples R China

[2] Temple Univ, Dept Elect & Comp Engn, Philadelphia, PA 19132 USA

来源：

DIGITAL SIGNAL PROCESSING | 2019年 / 87卷

基金：

中国国家自然科学基金;

关键词：

Human motion recognition; Radar; Deep learning; Recurrent neural network; Long short-term memory; BODY; CLASSIFICATION;

D O I：

10.1016/j.dsp.2019.01.013

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

We develop a novel radar-based human motion recognition technique that exploits the temporal sequentiality of human motions. The stacked recurrent neural network (RNN) with long short-term memory (LSTM) units is employed to extract sequential features for automatic motion classification. The spectrogram of raw radar data is used as the network input to utilize the time-varying Doppler and micro-Doppler signatures for human motion characterization. Based on experimental data, we verified that a stacked RNN with two 36-cell LSTM layers successfully classifies six different types of human motions. (C) 2019 Elsevier Inc. All rights reserved.

引用

页码：125 / 131

页数：7

共 36 条

[1]

Abadi M., 2015, TENSORFLOW LARGESCAL

[2] Radar Signal Processing for Elderly Fall Detection The future for in-home monitoring [J].

Amin, Moeness G. ;

Zhang, Yimin D. ;

Ahmad, Fauzia ;

Ho, K. C. .

IEEE SIGNAL PROCESSING MAGAZINE, 2016, 33 (02) :71-80

[3]

[Anonymous], EURASIP J ADV SIGNAL

[4]

[Anonymous], 2012, ADADELTA ADAPTIVE LE

[5]

[Anonymous], 2015, Nature, DOI [10.1038/nature14539, DOI 10.1038/NATURE14539]

[6]

[Anonymous], P SPIE

[7]

[Anonymous], SENSORS

[8]

[Anonymous], 2016, Time-Frequency Signal Analysis and Processing, DOI DOI 10.1016/B978-0-12-398499-9.00004-2

[9]

Boulic R., 1990, Visual Computer, V6, P344, DOI 10.1007/BF01901021

[10] Micro-doppler effect in radar: Phenomenon, model, and simulation study [J].

Chen, VC ;

Li, FY ;

Ho, SS ;

Wechsler, H .

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2006, 42 (01) :2-21

← 1 2 3 4 →