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

Human State Estimation System Implemented in an Office Deployable Getaway Based on Multiple Bio Information

Sayaka Nakaso, Jörg Güttler, Akira Mita and Thomas Bock
Pages 572-580 (2016 Proceedings of the 33rd ISARC, Auburn, USA, ISBN 978-1-5108-2992-3, ISSN 2413-5844)

This article is proposing a human state estimation system on the basis of multiple bio information implemented into a movable cover chair called 'Office Deployable Getaway'. The proposed system consists of 2 sub-systems; the first sub-system analyzes fatigue based on eye movement including blinking rate and eye closure time while the second sub-system analyzes breath frequency. These indicators are detected by applying image processing to IR images, using the Microsoft Kinect sensor. Hardware tests were conducted to determine the proper Microsoft Kinect (Kinect V1 or Kinect V2) and its position inside the chair to efficiently detect eye movement and respiration. The experimental results showed that these bio information could be measured appropriately under the condition that the Kinect V2 was set at the eye level opposite from the user. Based on the result, the implementation of the proposed system into the chair was carried out, installing the Kinect and a personal computer at appropriate positions. Finally, this system was tested in a real environment with test person sitting inside the chair; after the fatigue is analyzed over eye movement, breath frequency is analyzed. The results of these analyzations are indicated in the computer screen. This performance test showed that this system could be feasible for the realistic use. For future development, the authors will focus on audio system that triggers proper music based on estimated human state, which will be implemented into this chair.

Keywords: Human-Machine-Interaction, Breath Detection, Fatigue Analyzation, Human Mood, Eye Recognition, Ambient Assisted Living