A radar-based human activity recognition using a novel 3D point cloud classifier

Yu, Z., Zahid, A., Taha, A. , Taylor, W. , Rajab, K., Heidari, H. , Imran, M. A. and Abbasi, Q. H. (2022) A radar-based human activity recognition using a novel 3D point cloud classifier. IEEE Sensors Journal, 22(19), pp. 18218-18227. (doi: 10.1109/JSEN.2022.3198395)

[img] Text
276607.pdf - Accepted Version

12MB

Abstract

This article provides a new benchmark dataset for 3D point cloud classification in which the manually labelled human activity data exceeds 100 point clouds per frame and is capable of meeting the training needs for data-intensive learning approaches. In this study, a case study is considered for evaluating the benchmark using a deep LSTM neural network, which demonstrated a significant performance improvement over the state-of-the-art human activity recognition area. To date, numerous types of collection devices have been used in the recognition of human activities. However, due to the scarcity of training data, the task of 3D point cloud labelling has not yet made significant progress. To overcome this challenge, it is aimed to deduce this data requirements gap, allowing deep learning methods to reach their full potential in 3D point cloud tasks. The dataset used for this process is comprised of dense point clouds acquired with the static ground sensor by the NodeNs company supported MIMO radar (NodeNs ZERO 60 GHz IQ radar). It contains multiple types of human being data ranging from one to four individuals and encompasses a range of human action scenarios, including standing, sitting, picking up, falling, and walking. Furthermore, it also investigated sensor locations and requirements for human being data collection that is from a single subject to multiple subjects, as well as identified and analysed various sensing devices and applications that collect activity data. In this regard, a thorough study is conducted on several benchmark datasets, examining sensors, characteristics, activity categories, and other data. Finally, it compares and analyses the activity recognition methods used in several benchmark datasets based on the current study. Unlike existing devices, the new NodeNs sensor provides more accessible and straightforward point cloud data to capture human movement information. Depending on an advanced detection algorithm to process point cloud data it achieved more than 95% accuracy on the benchmark dataset.

Item Type:Articles
Additional Information:Zheqi Yu is funded by Joint industrial scholarship (Ref:308987) between the University of Glasgow and Transreport London Ltd.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Taha, Dr Ahmad and Yu, Zheqi and Imran, Professor Muhammad and Zahid, Mr Adnan and Heidari, Professor Hadi and Abbasi, Professor Qammer and Taylor, William
Authors: Yu, Z., Zahid, A., Taha, A., Taylor, W., Rajab, K., Heidari, H., Imran, M. A., and Abbasi, Q. H.
College/School:College of Science and Engineering > School of Engineering
College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
Journal Name:IEEE Sensors Journal
Publisher:IEEE
ISSN:1530-437X
ISSN (Online):1558-1748
Published Online:17 August 2022
Copyright Holders:Copyright © 2022 IEEE
First Published:First published in IEEE Sensors Journal 22(19): 18218-18227
Publisher Policy:Reproduced in accordance with the publisher copyright policy

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