Human Detection and Activity Classification Based on Micro-Doppler Signatures Using Deep Convolutional Neural Networks

被引:491
作者
Kim, Youngwook [1 ]
Moon, Taesup [2 ]
机构
[1] Calif State Univ Fresno, Fresno State Lyles Coll Engn, Dept Elect & Comp Engn, Fresno, CA 93740 USA
[2] Daegu Gyeongbuk Inst Sci & Technol, Dept Informat & Commun Engn, Daegu 711873, South Korea
关键词
Convolutional neural network; deep learning; human activity classification; human detection; micro-Doppler;
D O I
10.1109/LGRS.2015.2491329
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
We propose the use of deep convolutional neural networks (DCNNs) for human detection and activity classification based on Doppler radar. Previously, proposed schemes for these problems remained in the conventional supervised learning paradigm that relies on the design of handcrafted features. Whereas these schemes attained high accuracy, the requirement for domain knowledge of each problem limits the scalability of the proposed schemes. In this letter, we present an alternative deep learning approach. We apply the DCNN, one of the most successful deep learning algorithms, directly to a raw micro-Doppler spectrogram for both human detection and activity classification problem. The DCNN can jointly learn the necessary features and classification boundaries using the measured data without employing any explicit features on the micro-Doppler signals. We show that the DCNN can achieve accuracy results of 97.6% for human detection and 90.9% for human activity classification.
引用
收藏
页码:8 / 12
页数:5
相关论文
共 23 条
[1]  
[Anonymous], 2012, PREDICTION CANDIDATE
[2]  
[Anonymous], 1983, SOV MATH DOKL
[3]  
[Anonymous], 1989, P ADV NEUR INF PROC
[4]  
[Anonymous], CUDNN EFFICIEN UNPUB
[5]  
[Anonymous], 2012, P ADV NEUR INF PROC
[6]  
Bergstra J, 2012, J MACH LEARN RES, V13, P281
[7]  
Chen V.C., 2002, ARTECH HOUSE RADAR
[8]   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
[9]   Classification of human motions using empirical mode decomposition of human micro-Doppler signatures [J].
Fairchild, Dustin P. ;
Narayanan, Ram M. .
IET RADAR SONAR AND NAVIGATION, 2014, 8 (05) :425-434
[10]  
Glorot X., 2011, 14 INT C ART INT STA, P315, DOI DOI 10.1177/1753193410395357