The ToFEye includes ToF sensors, ToF imaging dataset (ToF Dataset), AI edge computing platform, ToFPose AI software model (ToFPose) and ToF abnormal posture recognition algorithm. ToFEye uses ToF sensors to capture spatial human images in Bathroom and Toilet, and applies AI and DL technologies to identify the abnormal posture action of ToF images. It can be applied to any space in the nursing place and achieve de-identification real-time abnormal posture notification purpose.

(1)100% de-identified posture recognition. (2)ToFEye is actually introduced into the hospital bathroom area to identify abnormal postures (including sitting on the toilet for a long time, staying in the bathroom for a long time, and falling and slipping) with 94.1% recall rate and 98.4% accuracy rate. (3)ToFEye constructs the world＇s first human body backbone data set based on ToF optical imaging, which can also be applied to any space in medical care settings.

ToFEye can be installed in hospitals, nursing institutions and other medical care places to establish 24-hour, active, de-identified patient abnormal behavior detection. In the future, big data analysis can be used to generate an abnormal behavior prediction model to send warning messages in advance before the patient falls, so that there are no blind spots in monitoring and time-lag care in warning, so as to achieve the goal of improving patient safety in hospitalization.