Human motion classification using a particle filter approach

Multiple model particle filtering applied to the micro-Doppler spectrum

Journal article (2013)
Department
Microelectronics (EEMCS) (TU Delft)
Copyright: © 2013 Cambridge University Press and the European Microwave Association
DOI: https://doi.org/doi:10.1017/S1759078713000366
More Info
expand_more

Published Date

23-04-2013

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.

Source:

International Journal of Microwave and Wireless Technologies, 5 (3), 2013

Faculty

Electrical Engineering, Mathematics and Computer Science

Department

Microelectronics

Abstract

In this article, a novel motion model-based particle filter implementation is proposed to classify human motion and to estimate key state variables, such as motion type, i.e. running or walking, and the subject’s height. Micro-Doppler spectrum is used as the observable information. The system and measurement models of human movements are built using three parameters (relative torso velocity, height of the body, and gait phase). The algorithm developed has been verified on simulated and experimental data.

Files

Groot_harmanny.pdf
(pdf | 0.755 Mb)