Detecting Multiple People with Low-Resolution Thermal Sensors in Smart Spaces

This paper presents a framework to accurately and non-intrusively detect the number of people in an environment. Our system setup uses only ambient 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. Our experiments demonstrate that algorithm selection is very important, but with careful selection, we can obtain up to 100% accuracy. Also, we prove that sensor placement plays a crucial role on the system performance, where placing the sensor on the room ceiling yields to the best results.