Gait Classification Based on Micro-Doppler Features

Yang, L., Li, G., Ritchie, M., Fioranelli, F. and Griffiths, H. (2017) Gait Classification Based on Micro-Doppler Features. In: 2016 CIE International Conference on Radar (Radar 2016), Guangzhou, China, 10-13 Oct 2016, (doi:10.1109/RADAR.2016.8059301)

[img]
Preview
Text
150351.pdf - Accepted Version

572kB

Publisher's URL: http://ieeexplore.ieee.org/document/8059301/

Abstract

This paper focuses on the classification of human gaits based on micro-Doppler signatures. The micro-Doppler signatures can represent detailed information about the human gaits, which helps in judging the threat of a personnel target. The proposed method consists of three major steps. Firstly, the micro-Doppler signatures are obtained by performing time-frequency analysis on the radar data. Then two micro-Doppler features are extracted from the time-frequency domain. Finally, the one-versus-one support vector machine (SVM) is used to realize multi-class classification. Experiments on real data show that, with the selected features, high classification accuracy of the human gaits of interest can be achieved.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Fioranelli, Dr Francesco and Ritchie, Mr Matthew
Authors: Yang, L., Li, G., Ritchie, M., Fioranelli, F., and Griffiths, H.
College/School:College of Science and Engineering > School of Engineering > Systems Power and Energy
Copyright Holders:Copyright © 2017 IEEE
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher.

University Staff: Request a correction | Enlighten Editors: Update this record