Time-Frequency Resolution Analysis for Continuous Human Activity Recognition using Radar Networks

Conference Paper (2024)
Author(s)

Ronny Guendel (TU Delft - Microwave Sensing, Signals & Systems)

Francesco Fioranelli (TU Delft - Microwave Sensing, Signals & Systems)

O. Yarovoy (TU Delft - Microwave Sensing, Signals & Systems)

Microwave Sensing, Signals & Systems
DOI related publication
https://doi.org/10.1109/iWAT57102.2024.10535806
More Info
expand_more
Publication Year
2024
Language
English
Microwave Sensing, Signals & Systems
Pages (from-to)
341-344
ISBN (electronic)
9798350314755
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The effect of different time-frequency (TF) resolution values is analyzed in the context of Human Activity Recognition (HAR) using multiple radars distributed in a network. Specifically, different spectrograms computed with various Short-Time Fourier Transform (STFT) window lengths and Morse wavelet transform are compared as input representation to a Convolutional Neural Network (CNN), together with a coherent combination of multiple spectrograms. The study emphasizes the importance of selecting appropriate window sizes for TF analysis and for classification, balancing the observation time with the physical duration of the diverse activities, and also avoiding correlation between different data samples that may compromise the generalization ability of the method. The results employing this coherent sensor fusion demonstrate the efficacy of the investigated method, achieving an F1 score of 0.943 on a challenging public dataset containing 9 activities performed by 15 participants.

Files

Time-Frequency_Resolution_Anal... (pdf)
(pdf | 1.9 Mb)
- Embargo expired in 11-02-2025
License info not available