Title: Development of an awakening detection system with the NN and adaptation for fluctuation of brightness quantity in the captured image

Authors: Nobuhisa Yamanaka, Hironobu Satoh, Fumiaki Takeda

Addresses: Kochi University of Technology, 185 Miyanokuchi, Tosayamada, Kami, Kochi 782-8502, Japan. ' Kochi University of Technology, 185 Miyanokuchi, Tosayamada, Kami, Kochi 782-8502, Japan. ' Kochi University of Technology, 185 Miyanokuchi, Tosayamada, Kami, Kochi 782-8502, Japan

Abstract: Recently, accidents such that seniors fall down from the bed in hospitals are increased. To prevent these accidents, we have developed an awakening detection system using neural network. In this paper, we adopt a face extractive method to execute more detail extraction of the objective person|s image from the background. We show its feasibility with experimental results. In addition, to confirm the detection capability in the clinical site, the detection experiment using the captured image in the clinical site is conducted. From the result, the detection success rate was low. So, we analyse the captured image in the clinical site. From the analysis of the histogram, it proves that the fluctuation of brightness quantity make decrease the detection capability. Therefore, to decrease this influence, the histogram of the captured image is equalised. Finally, it is verified that the histogram equalisation reduces the effect of fluctuation of brightness quantity.

Keywords: wakening detection; image capture; NNs; neural networks; brightness quantity; feature extraction; histogram equalisation; elderly patients; healthcare technology; patient falls; patient waking; old people; patient observation; patient monitoring.

DOI: 10.1504/IJISTA.2010.036583

International Journal of Intelligent Systems Technologies and Applications, 2010 Vol.9 No.3/4, pp.286 - 299

Published online: 04 Nov 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article