Development of an Awaking Behavior Detection System with Kinect

Abstract

The purpose of this study is detecting unsafe behavior of the person lying on the bed and warning caregivers that a person is falling down from the bed. However, in the dark room at night, the detection ability of previous system is low, because the brightness adjustment processing of a Web camera is not able to adjust brightness of the dark room. In this paper, we propose a new detection system using Kinect. Kinect has a depth sensor consisted of infrared leaser. And, Kinect is able to measure distance between Kinect and an object in the dark room. Moreover, the behavior of an old person is extracted from measured data by Kinect. By using Kinect, it is considered that the awakening behavior detection system is able to be used in the dark room at night. In this paper, the awakening detection system using Kinect is shown. And, in experiment, the capability of the proposed system have been verified. From the result of the experiment, the detection rate of the safe behavior have been 94%. And, the detection rate of the unsafe behavior have been 80%. © Springer International Publishing Switzerland 2014.