Dual-Scale Doppler Attention for Human Identification

Citations

WEB OF SCIENCE

2
Citations

SCOPUS

4

초록

This paper considers a Deep Convolutional Neural Network (DCNN) with an attention mechanism referred to as Dual-Scale Doppler Attention (DSDA) for human identification given a micro-Doppler (MD) signature induced as input. The MD signature includes unique gait characteristics by different sized body parts moving, as arms and legs move rapidly, while the torso moves slowly. Each person is identified based on his/her unique gait characteristic in the MD signature. DSDA provides attention at different time-frequency resolutions to cater to different MD components composed of both fast-varying and steady. Through this, DSDA can capture the unique gait characteristic of each person used for human identification. We demonstrate the validity of DSDA on a recently published benchmark dataset, IDRad. The empirical results show that the proposed DSDA outperforms previous methods, using a qualitative analysis interpretability on MD signatures.

키워드

deep learning; human identification; micro-Doppler radar; fine-grained feature analysis; HUMAN ACTIVITY CLASSIFICATION; MICRO-DOPPLER; NEURAL-NETWORKS; RADAR
제목
Dual-Scale Doppler Attention for Human Identification
저자
Yoon, Sunjae; Kim, Dahyun; Hong, Ji Woo; Kim, Junyeong; Yoo, Chang D.
DOI
10.3390/s22176363
발행일
2022-09
유형
Article
저널명
Sensors
권
22
호
17

파일 다운로드

Thumbnail