Privacy-preserving, thermal vision with human in the loop fall detection alert system

Naser, A ORCID logoORCID: https://orcid.org/0000-0001-5969-1756, Lotfi, A ORCID logoORCID: https://orcid.org/0000-0002-5139-6565, Mwanje, MD and Zhong, J, 2022. Privacy-preserving, thermal vision with human in the loop fall detection alert system. IEEE Transactions on Human-Machine Systems. ISSN 2168-2291

[thumbnail of 1596676_Lotfi.pdf]
Preview
Text
1596676_Lotfi.pdf - Post-print

Download (4MB) | Preview

Abstract

To support the independent living of older adults in their own homes, it is essential to identify their abnormal behaviors before triggering an automated alert system. Existing normal vision sensing approaches to detect human falls in the activities of daily living (ADL) experienced acceptability issues due to outstanding privacy concerns when they are deployed in personal environments. Besides, false alerts (false-positive) fall detection has not been addressed thoroughly in systems that report abnormal human behaviors as emergency alerts to the information support. This article proposes a novel human-in-the-loop fall detection approach in the ADLs using a low-resolution thermal sensor array. The motivation for enabling a human interactive model, fall detection confirmation, is to influence resource efficiency by reducing false-positive alerts while keeping the false-negative fall predictions as low as possible. The proposed approach is based on the motion sequence classification of human movements using a recurrent neural network. The proposed approach is evaluated with comprehensive experiments using different learning techniques, users, and domestic environment conditions. This article shows a performance accuracy of 99.7% to detect human falls from various typical ADLs.

Item Type: Journal article
Publication Title: IEEE Transactions on Human-Machine Systems
Creators: Naser, A., Lotfi, A., Mwanje, M.D. and Zhong, J.
Publisher: Institute of Electrical and Electronics Engineers
Date: 9 September 2022
ISSN: 2168-2291
Identifiers:
Number
Type
10.1109/thms.2022.3203021
DOI
1596676
Other
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 12 Sep 2022 09:26
Last Modified: 12 Sep 2022 09:28
URI: https://irep.ntu.ac.uk/id/eprint/47012

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year