Development of an Awaking Behavior Detection System with Kinect

  • Hironobu Satoh
  • Kyoko Shibata
  • Tomohito Masaki
Part of the Communications in Computer and Information Science book series (CCIS, volume 435)


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%.


Awaking behavior detection system Neural network Kinect 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ikeda, R., Satoh, H., Takeda, F.: Development of Awaking Behavior Detection System Nursing Inside the House. In: International Conference on Intelligent Technology 2006, pp. 65–70 (2006)Google Scholar
  2. 2.
    Matubara, T., Satoh, H., Takeda, F.: Proposal of an Awaking Detection System Adopting Neural Network in Hospital Use. In: World Automation Congress 2008 (2008)Google Scholar
  3. 3.
    Satoh, H., Takeda, F., Shiraishi, Y., Ikeda, R.: Development of a Awaking Behavior Detection System Using a Neural Network. IEEJ Trans. EIS 128(11), 1649–1656 (2008)CrossRefGoogle Scholar
  4. 4.
    Yamanaka, N., Satoh, H., Shiraishi, Y., Matsubara, T., Takeda, F.: Proposal of The Awakening Detection System Using Neural Network and It’s Verification. In: The 52nd The Institute of Systems, Control and information Engineers (2008)Google Scholar
  5. 5.
    Satoh, H., Takeda, F.: Verification of the Effectiveness of the Online Tuning System for Unknown Person in the Awaking Behavior Detection System. In: Omatu, S., Rocha, M.P., Bravo, J., Fernández, F., Corchado, E., Bustillo, A., Corchado, J.M. (eds.) IWANN 2009, Part II. LNCS, vol. 5518, pp. 272–279. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Haykin, S.: Neural Networks a comprehensive foundation, New Jersey, USA, pp. 161–173 (1998)Google Scholar
  7. 7.
    Yoshua, B., Pascal, L., Dan, P., Hugo, L.: Greedy Layer-Wise Training of Deep Networks. In: Advances in Neural Information Processing Systems 19, pp. 153–160 (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Hironobu Satoh
    • 1
  • Kyoko Shibata
    • 2
  • Tomohito Masaki
    • 1
  1. 1.Kochi National College of TechnologyNangokuJapan
  2. 2.Kochi University of TechnologyTosayamada, KamiJapan

Personalised recommendations