Thermography-based assessment of mean radiant temperature and occupancy in healthcare facilities.

Paper in proceeding, 2023

Due to its high demands regarding indoor environmental conditions, healthcare facilitiesare associated with high energy consumption. To move forward towards more demand driven andenergy reduced conditioning, information on occupancy and temperature boundary conditions arecrucial. Thermography-based systems enable data acquisition regarding both aspects in high localresolution. In this publication, we propose a thermography system that may be used for monitoring ofrooms in healthcare facilities. It is set up using a 160 x 120 px thermography sensor and Raspberry Picomputer for data acquisition and processing. The sensors are mounted on walls to capture the insideof the room including patients, staff, and visitors. We evaluate the mean radiant temperature based onthe individual inner surfaces of the room. The algorithm aggregates wall, floor and ceiling surfacetemperatures within the field of view of the sensor. For occupancy estimation inside the room, weapply a convolutional neural network (CNN). It is based on a pre-trained network and retrained usinga partial dataset collected during the field study. To improve robustness of the algorithm several datapre-processing steps are conducted, that include image filters and redundancy testing. The system isevaluated based on data collected in a field study conducted inside MHH Hospital in Hannover,Germany. Several patients’ rooms and a staff room are monitored over a period of 6 weeks, with thegoal of evaluating indoor environmental data. The measurement period is inside the heating period inwinter and different room layouts are considered. For reference, an indoor environmental qualitymeasurement device is used to simultaneously measure air temperature, globe temperature and otherIEQ parameters. Measured data of the reference system agree well with the thermography system.Deviations between both are less than 1 K in radiant temperature for most scenarios and measurementsetups. Estimated occupancy is compared to a ground truth derived from manual processing of thecaptured thermography data. Finally, results of the field study are discussed together with the systemsadvantages and limitations with regard to privacy considerations.