Fall detection system for people using video surveillance

Abstract

Falls are the second cause of death in the world. This paper proposes a fall detection system for people, based on a Kinect 2.0 sensor that allows monitoring from one to six individuals and an alarm system that sends a message with an image to the caregiver's email. The biomechanical analysis of the fall was performed using the iPi Mocap Studio software, and the fall detection algorithm was developed in LabVIEW, allowing the measurement of position and velocity of the selected point in the person’s skeletonization. The system achieved a 95.8% accuracy rate.