Non-Intrusive Presence Detection and Position Tracking for Multiple People Using Low-Resolution Thermal Sensors

Abstract

This paper presents a framework to accurately and non-intrusively detect the number of people in an environment and track their positions. Different from most of the previous studies, our system setup uses only ambient thermal sensors with low-resolution, using no multimedia resources or wearable sensors. This preserves user privacy in the environment, and requires no active participation by the users, causing no discomfort. We first develop multiple methods to estimate the number of people in the environment. Our experiments demonstrate that algorithm selection is very important, but with careful selection, we can obtain up to 100% accuracy when detecting user presence. In addition, we prove that sensor placement plays a crucial role in the system performance, where placing the sensor on the room ceiling yields to the best results. After accurately finding the number of people in the environment, we perform position tracking on the collected ambient data, which are thermal images of the space where there are multiple people. We consider position tracking as static activity detection, where the user's position does not change while performing activities, such as sitting, standing, etc. We perform efficient pre-processing on the data, including normalization and resizing, and then feed the data into well-known machine learning methods. We tested the efficiency of our framework (including the hardware and software setup) by detecting four static activities. Our results show that we can achieved up to 97.5% accuracy when detecting these static activities, with up to 100% class-wise precision and recall rates. Our framework can be very beneficial to several applications such as health-care, surveillance, and home automation, without causing any discomfort or privacy issues for the users.

Device-Free Localization Using Privacy-Preserving Infrared Signatures Acquired From Thermopiles and Machine Learning

“…Singh et al [31] compared the application of various Machine Learning (ML) classifiers for the detection and activity recognition of multiple human subjects using thermopile sensors. Similarly, Tateno et al [32] and Tao et al [33] used deep learning networks for fall detection and activity recognition respectively by utilizing ceiling-mounted sensors.…”

Activity Recognition in Residential Spaces with Internet of Things Devices and Thermal Imaging

“…Human activity can be recognized using various technologies namely sensors, video cameras, etc. [ 2 ], and using traditional or machine learning approaches [ 3 , 4 ]. Human activity recognition (HAR) is an important module for home monitoring systems for smart homes.…”

“…These types of systems can be used to provide safety to children and elderly people living in the home [5]. The combination of two emerging fields, Internet of Things (IoT) and Machine learning has achieved promising results for HAR [4,6]. The main data source for the task of activity recognition is sensors.…”

Occupancy Prediction Using Low-Cost and Low-Resolution Heat Sensors for Smart Offices

“…Jeong et al [ 18 ] showed that an adaptive thresholding method could help to detect people while using low-resolution heat sensors. Singh et al [ 19 ] used adaptive thresholding and the binary results for understanding whether people are on the floor, in a standing or sitting position. Next, they extended their work towards a multiple sensor application [ 20 ].…”