Fall Detection Using Deep Learning in Range-Doppler Radars

In this paper, we propose an approach that uses deep learning to detect a human fall. The proposed approach automatically captures the intricate properties of the radar returns. In order to minimize false alarms, we fuse information from both the time-frequency and range domains. Experimental data i...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on aerospace and electronic systems 2018-02, Vol.54 (1), p.180-189
Main Authors: Jokanovic, Branka, Amin, Moeness
Format: Article
Language:English
Subjects:
Deep learning
detection
doppler
Doppler radar
fall
Fall detection
False alarms
Feature extraction
fusion
human motion
Machine learning
Principal components analysis
Radar detection
range
sparse autoencoder
Spectrogram
Time-frequency analysis
time-frequency domain
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:In this paper, we propose an approach that uses deep learning to detect a human fall. The proposed approach automatically captures the intricate properties of the radar returns. In order to minimize false alarms, we fuse information from both the time-frequency and range domains. Experimental data is used to demonstrate the superiority of the deep learning based approach in comparison with the principal component analysis method and those methods incorporating predefined physically interpreted features.
ISSN:0018-9251
1557-9603
DOI:10.1109/TAES.2017.2740098