21 May 2015 High-resolution time-frequency distributions for fall detection
Author Affiliations +
In this paper, we examine the role of high-resolution time-frequency distributions (TFDs) of radar micro-Doppler signatures for fall detection. The work supports the recent and rising interest in using emerging radar technology for elderly care and assisted living. Spectrograms have been the de facto joint-variable signal representation, depicting the signal power in both time and frequency. Although there have been major advances in designing quadratic TFDs which are superior to spectrograms in terms of detailing the local signal behavior, the contributions of these distributions in the area of human motion classifications and their offerings in enhanced feature extractions have not yet been properly evaluated. The main purpose of this paper is to show the effect of using high-resolution TFD kernels, in lieu of spectrogram, on fall detection. We focus on the extended modified B-distribution (EMBD) and exploit the level of details it provides as compared with the coarse and smoothed time-frequency signatures offered by spectrograms.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Moeness G. Amin, Moeness G. Amin, Yimin D. Zhang, Yimin D. Zhang, Boualem Boashash, Boualem Boashash, } "High-resolution time-frequency distributions for fall detection", Proc. SPIE 9461, Radar Sensor Technology XIX; and Active and Passive Signatures VI, 94611B (21 May 2015); doi: 10.1117/12.2180139; https://doi.org/10.1117/12.2180139


Back to Top