Exploring video based thermal perception identification

摘要: HVAC systems in buildings are responsible for majority of the annual energy consumption both for residential and commercial buildings. Efficient management of energy consumption for air conditioning systems could play a major role in achieving energy sustainability objectives. The main driving factor in determining operational settings of an air conditioning system is indoor thermal condition and its association with occupants’ satisfaction. In conventional thermal comfort assessment techniques (such as PMV-PPD model), lack of real-time information about occupants’ characteristics calls for conservative assumptions that could consequently result in inefficient operations as it has been reported in literature. Alternative solutions have been proposed for thermal comfort identification by using sensors that help measure different physiological variables from occupants’ bodies. In majority of the cases, the sensor needs to be installed on the occupants’ skin. In this paper, we investigated the feasibility of proposing a non-invasive, automated framework to continuously optimize occupants’ satisfaction for energy optimization. Personal computers cameras are ubiquitous devices which provide an opportunity to determine occupants’ thermal perception without distraction. We explored the association between occupants’ thermal perception and the physiological signals that can be measured through facial videos, captured by a computer webcam, by focusing on heart rate as one of the physiological variables, which is influenced by thermoregulation system and can be extracted by applying image processing techniques. The study was conducted by …