3D Convolutional Neural network for Home Monitoring using Low Resolution Thermal-sensor Array

Lili Tao, Timothy Volonakis, Bo Tan, Ziqi Zhang, Yanguo Jing, Melvyn Smith

Research output: Contribution to conferencePaperpeer-review

Abstract

The recognition of daily actions, such as walking, sitting or
standing, in the home is informative for assisted living, smart
homes and general health care. A variety of actions in complex
scenes can be recognised using visual information. However
cameras succumb to privacy concerns. In this paper, we present
a home activity recognition system using an 8×8 infared sensor array. This low spatial resolution retains user privacy, but is still a powerful representation of actions in a scene. Actions are recognised using a 3D convolutional neural network, extracting not only spatial but temporal information from video sequences. Experimental results obtained from a publicly available dataset Infra-ADL2018 demonstrate a better performance of the proposed approach compared to the state-of-the-art. We show that the sensor is considered better at detecting the occurrence of falls and activities of daily living. Our method achieves an overall accuracy of 97.22% across 7 actions with a fall detection sensitivity of 100% and specificity of 99.31%
Original languageEnglish
Publication statusAccepted/In press - 21 Feb 2019
Event3rd IET International Conference on Technologies for Active and Assisted Living - IET London: Savoy Place, London, United Kingdom
Duration: 25 Mar 201925 Mar 2019
https://events.theiet.org/techaal/

Conference

Conference3rd IET International Conference on Technologies for Active and Assisted Living
Country/TerritoryUnited Kingdom
CityLondon
Period25/03/1925/03/19
Internet address

Fingerprint

Dive into the research topics of '3D Convolutional Neural network for Home Monitoring using Low Resolution Thermal-sensor Array'. Together they form a unique fingerprint.

Cite this