Deep-Learning for Occupancy Detection Using Doppler Radar and Infrared Thermal Array Sensors

Abstract

An accurate, real-time monitoring of the occupancy state of each space is a necessity for applications such as energy-aware smart buildings. In this paper, we have studied the feasibility of using Doppler Radar Sensors (DRS) and Infrared Thermal Array Sensors (ITA) to build an effective occupancy detection framework. The proposed sensor types are cost-effective and protect the privacy of the occupants. We have utilized Deep Neural Networks (DNN) to analyze the sensor data without any need for specialized feature extraction that is necessary for classical machine learning approaches. The results are indicative of the feasibility and the reliability of using both sensor types for detection of the occupancy state. While a threshold-based approach reached an average accuracy of 84.3% and 86% for the DRS and ITA sensors respectively, DNN models were able to achieve average accuracies of 98.9% and 99.96% for the DRS and ITA sensors respectively, thereby demonstrating the feasibility and success of the proposed framework.

Can Radar Remote Life Sensing Technology Help Combat COVID-19?

“…2014). Conventional occupancy sensors are typically motion sensors such as passive infrared (PIR) sensors (Abedi et al, 2019). A significant drawback of PIR sensors is the high rate of false detection rate as it only recognizes motion (Abedi et al, 2019).…”

“…Conventional occupancy sensors are typically motion sensors such as passive infrared (PIR) sensors (Abedi et al, 2019). A significant drawback of PIR sensors is the high rate of false detection rate as it only recognizes motion (Abedi et al, 2019). When subjects are stationary in a home environment, traditional occupancy sensors cannot determine the true presence of humans (Yavari et al, 2014).…”

“…When subjects are stationary in a home environment, traditional occupancy sensors cannot determine the true presence of humans (Yavari et al, 2014). An alternative to the PIR sensor is video camera-based sensing technology (Abedi et al, 2019). However, video-image-based occupancy detection is accompanied by considerable privacy concerns (Abedi et al, 2019).…”

“…An alternative to the PIR sensor is video camera-based sensing technology (Abedi et al, 2019). However, video-image-based occupancy detection is accompanied by considerable privacy concerns (Abedi et al, 2019). The detection of human cardiopulmonary motion with Doppler radar could provide a promising approach to overcome the conventional sensor problems of false triggering and dead spots when humans are sedentary (Yavari et al, 2018).…”

Optimizing Clinical Spatial Resources with IoT

“…Looking beyond healthcare research there is a wealth of literature using a variety of sensors to detect human presence. Recent methods of human occupation prediction include monitoring of WiFi traffic [18], CO2 sensors [19,20] often combined with Machine Learning, with promising recent research in privacy-protective environments using LIDAR [21] Doppler radar systems [22] and audio-processing [23]. Each of these has increased challenges in a healthcare setting however, with the latter having increased privacy concerns in clinical settings beyond domestic or commercial applications.…”