Development of non-restrictive sensing system for sleeping person using fiber grating vision sensor

We have developed a visual sensing system for detecting elderly or sick people's paroxysm accidents while in bed. The system utilizes our developed fiber grating vision sensor to obtain 3D information about the person on the bed. A visual sensor installed over the sleeping person monitors respiration and rolling over of the person nonrestrictively without disturbing his/her privacy. This paper describes the configuration of the system for finding paroxysm accidents while asleep using a fiber grating vision sensor. We installed our trial system and performed an experiment assuming various situations on the bed. In this experiment, we proved that the system detects the respiration pattern with accuracy.