Publications / 2016 Proceedings of the 33rd ISARC, Auburn, USA

A Face Recognition System for Automated Door Opening with parallel Health Status Validation Using the Kinect v2

A. Ogawa , A. Mita, C. Georgoulas and T. Bock
Pages 132-140 (2016 Proceedings of the 33rd ISARC, Auburn, USA, ISBN 978-1-5108-2992-3, ISSN 2413-5844)

Nowadays it is said that extending the healthy life expectancy is important in the aging society target group. Of course it is important for every single-person household to be regularly checked upon their safety, but especially for elderly people the importance is higher at the point of healthy living, because this particular target group comprises a higher accidents rate. Therefore, the authors here propose the design and implementation of an unobtrusive vision system for single-person households, particularly for elderly people, based on the Microsoft Kinect v2. The entrance area of the home environment is here considered, where the monitoring system is activated upon while the user approaches, in order to first detect and calculate the user?s fatigue levels, as well as to secondly identify the user by facial recognition, in order to actuate a door opening mechanism. The proposed system algorithm is divided into two distinct phases. The first phase concerns the acquisition of the user knee position while walking up a staircase in order to calculate fatigue. The second phase comprises the face recognition based door opening method. The proposed system has been successfully tested, and it could undoubtedly comprise an unobtrusive health status validation and automated door opening solution for elderly people in single-person households.

Keywords: Computer Vision, Kinect v2, Face Recognition, Fatigue Detection, Ambient Assisted Living