Multi-Person Recognition Using Separated Micro-Doppler Signatures

It is challenging to recognize individuals when they move in the radar field of view due to the superimposition of micro-Doppler signatures. This paper presents a multi-person recognition approach by separating micro-Doppler signatures of multiple persons into their individual components. The prelim...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2020-06, Vol.20 (12), p.6605-6611
Main Authors: Huang, Xuejun, Ding, Jinshan, Liang, Dongxing, Wen, Liwu
Format: Article
Language:English
Subjects:
Chirp
deep neural network (DNN)
Doppler effect
Doppler radar
Feature extraction
Field of view
micro-Doppler signatures
multi-task learning network
Neural networks
Personnel
Personnel recognition
Radar signatures
Radar tracking
Recognition
Separation
Superposition (mathematics)
Waveforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:It is challenging to recognize individuals when they move in the radar field of view due to the superimposition of micro-Doppler signatures. This paper presents a multi-person recognition approach by separating micro-Doppler signatures of multiple persons into their individual components. The preliminary separation can be obtained by their range difference in a high resolution radar. A multi-task learning network is designed for both the fine separation of micro-Doppler signatures and the personnel recognition. A frequency modulated continuous waveform (FMCW) radar that operates at 77 GHz for automotive applications is used in experiments. The proposed deep-neural-network-based approach gives a convincing result in the test.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2020.2977170