Use of Thermal Sensors for Fall Detection in a Simulated Toilet Environment

Abstract

Falls are likely to occur in a toilet. However, people typically are alone when they use the toilet; thus, if a fall occurs, it may be difficult to ask for help. Therefore, we constructed a fall detection system using a thermal image sensor that cannot distinguish details, such as a face, and has high suitability for the toilet environment. In this study, we investigate the influence of the sensor position on the fall discrimination rate. Sensors were installed at four locations and normal toilet movements and falling postures were recorded using eight healthy adults. Discrimination formulas were prepared using thermal images obtained for four subjects, and discrimination rates of falling postures were calculated for the remaining four subjects, which were then compared relative to sensor positions. The highest discrimination rate (95.7%) was obtained with the sensor installed in front of the toilet at the height of the body center of the subject sitting on the toilet. The lowest discrimination rate (60.2%) was obtained with the sensor installed in front of the toilet and close to the ceiling with respect to the subject sitting on the toilet. To detect falls using thermal imaging, sensor positions should be based on various factors, such as whether the entire body can be imaged relative to the falling posture without depending only on the height and direction or whether the difference between normal activity and falling posture is clear, including the environment of the toilet and the assumed fall situation.

Machine Learning-Based Classification of Human Behaviors and Falls in Restroom via Dual Doppler Radar Measurements

“…However, because sensors without privacy issues are more suitable for restroom monitoring, approaches using infrared-based thermal sensors and radars have been recently studied. However, most studies classify situations as normal or dangerous behaviors [9,10]. Although thermal sensors show a sufficiently accurate classification, detailed behaviors were not classified because the sensors cannot detect the motion information directly.…”

“…Hence, investigations of restroom monitoring have been limited. Even though infrared, thermal, sensor-based posture estimation in restrooms has been proposed [9,10], its measurement accuracy depends on the temperature of the toilet and of the subject's clothing.…”