Machine Learning Techniques for Device-Free Localization Using Low-Resolution Thermopiles

Abstract

Indoor device-free localization (DFL) has many uses, including aged care, location-based services, ambient-assisted living, and fire safety management. In recent publications, thermopile sensors (very low-resolution infrared cameras) have been shown as being able to localize individuals while preserving their privacy. This article reports the performance evaluation of a large number of supervised machine learning techniques for the localization of a target using a ceiling-mounted thermopile. The algorithms were trained and validated using a large data set constructed from an individual walking arbitrary paths with the accurate ground truth provided by a virtual reality system. For robust performance evaluation, the algorithms were tested with data sets collected on a different day with several other subjects. A 2-D convolutional neural network exploiting spatial correlation and several recurrent neural network structures exploiting temporal correlation among the captured data provided the most accurate localization performance. Several data sets, constructed from the thermopile’s readings for four individual targets, were made available online for other researchers to use.