No Cover Image

Conference Paper/Proceeding/Abstract 623 views

Continuous Human Activity Recognition using Radar Imagery and Dynamic Time Warping

Ruchita Mehta, Vasile Palade, Sara Sharifzadeh Orcid Logo, Bo Tan, Yordanka Karayaneva

2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)

Swansea University Author: Sara Sharifzadeh Orcid Logo

Full text not available from this repository: check for access using links below.

DOI (Published version): 10.1109/icmla55696.2022.00076

Abstract

Remote Human Activity Recognition (HAR) in a private residential area has a beneficial influence on the elderly population's life, since this group of people require regular monitoring of health conditions. This paper addresses the problem of continuous detection of daily human activities using...

Full description

Published in: 2022 21st IEEE International Conference on Machine Learning and Applications (ICMLA)
Published: IEEE 2022
Online Access: http://dx.doi.org/10.1109/icmla55696.2022.00076
URI: https://cronfa.swan.ac.uk/Record/cronfa63203
Abstract: Remote Human Activity Recognition (HAR) in a private residential area has a beneficial influence on the elderly population's life, since this group of people require regular monitoring of health conditions. This paper addresses the problem of continuous detection of daily human activities using mm-wave Doppler radar. Unlike most previous research, this work records the data in terms of continuous series of activities rather than individual activities. These series of activities are similar to real-life activity patterns. The Dynamic Time Warping (DTW) algorithm is used for the detection of human activities in the recorded time series of data and compared to other time-series classification methods. DTW requires less amount of labelled data. The input for DTW was provided using three strategies, and the obtained results were compared against each other. The first approach uses the pixel-level data of frames (named UnSup-PLevel). In the other two strategies, a Convolutional Variational Autoencoder (CVAE) is used to extract Un-Supervised Encoded features (UnSup-EnLevel) and Supervised Encoded features (Sup-EnLevel) from the series of Doppler frames. Results demonstrates the superiority of the Sup-EnLevel features over UnSup-EnLevel and UnSup-PLevel strategies. However, the performance of the UnSup-PLevel strategy worked surprisingly well without using annotations.
College: Faculty of Science and Engineering

Similar Items