Complex Field-based Fusion Network for Human Activities Classification With Radar

Guo, J., Shu, C., Zhou, Y., Wang, K., Fioranelli, F. , Romain, O. and Le Kernec, J. (2021) Complex Field-based Fusion Network for Human Activities Classification With Radar. In: IET International Radar Conference 2020, Chongqing City, China, 4-6 Nov 2020, pp. 68-73. ISBN 9781839535406 (doi: 10.1049/icp.2021.0572)

Abstract

In the context of assisted living, human activity recognition (HAR) is of increased importance to maintain people at home living independently longer. Compared with directly using spectrograms (μD) or range profiles (RP) as inputs for classification discarding either range or explicit Doppler information, range-Doppler-surface (RDS) can more fully represent the information contained in the observed activities. However, because the data are collected from different activities, people, and locations, the RDS has a requires non-trivial adjustments for pre-processing as discussed in this paper to maintain the number of points in the RDS to fixed integer. Although it has improved performance (92%) compared to CNN (90%), this algorithm also discards phase information as most algorithms do in HAR with radar. In contrast, the phase information of the range-Doppler domain, although its performance was not the best (88%), it had no obvious weakness in the recognition of all the movements. Our proposed complex field-based fusion network (CFFN) combines the amplitude and phase which improves both the accuracy of classification (94%) as well as accelerating training time by 12.5%.

• Item Type: Conference Proceedings
• Additional Information: The authors thank Glasgow College - UESTC and the British Council 515095884 and Campus France 44764WK-PHC Alliance France-UK for their financial support.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Romain, Professor Olivier and Fioranelli, Dr Francesco and Le Kernec, Dr Julien
• Authors: Guo, J., Shu, C., Zhou, Y., Wang, K., Fioranelli, F., Romain, O., and Le Kernec, J.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Systems Power and Energy
• ISBN: 9781839535406
• Copyright Holders: Copyright © 2021 The Institution of Engineering and Technology
• First Published: First published in IET International Radar Conference 2020: 68-73
• Publisher Policy: Reproduced in accordance with the publisher copyright policy

Related URLs

• Organisation