An Efficient Fall Detection Method for Elderly Care System

Authors: S. Sowmyayani, P. Arockia Jansi Rani

Abstract:

Fall detection is one of the challenging problems in elderly care system. The objective of this paper is to identify falls in elderly care system. In this paper, an efficient fall detection method is proposed to identify falls using correlation factor and Motion History Image (MHI). The proposed method is tested on URF (University of Rzeszow Fall detection) dataset and evaluated with some efficient measures like sensitivity, specificity, precision and classification accuracy. It is compared with other recent methods. The experimental results substantially proved that the proposed method achieves 1.5% higher sensitivity when compared to other methods.

Keywords: Pearson correlation coefficient, motion history image, human shape identification.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.2643710

References:

[1] H. Foroughi, A. Naseri, A. Saberi, and H. S. Yazdi, An Eigenspace-Based Approach for Human Fall Detection Using Integrated Time Motion Image and Neural Network, 9th IEEE International Conference on Signal Processing (ICSP), pp. 1499-1503, 2008.
[2] S. J. McKenna and H. Nait-Charif, Summarising Contextual Activity and Detecting Unusual Inactivity in a Supportive Home Environment, 17th IEEE International Conference on Pattern Recognition, Vol. 4, pp. 323-326, 2004.
[3] H. Foroughi, B. S. Aski, and H. Pourreza, Intelligent Video Surveillance for Monitoring Fall Detection of Elderly in Home Environments, 11th IEEE International Conference on Computer and Information Technology (ICCIT), pp. 219-224, 2008.
[4] J. Tao, M. Turjo, M. F. Wong, M. Wang and Y. P. Tan: Fall Incidents Detection for Intelligent Video Surveillance, Fifth IEEE International Conference on Information, Communications and Signal Processing, pp. 1590-1594, 2005.
[5] C. Rougier, J. Meunier, A. St-Arnaud and J. Rousseau, Fall Detection from Human Shape and Motion History using Video Surveillance, 21st IEEE International Conference on Advanced Information Networking and Applications Workshops (AINAW'07), pp. 875-880, 2007.
[6] C. W. Lin and Z. H. Ling, Automatic Fall Incident Detection in Compressed Video for Intelligent Homecare, 16th IEEE International Conference on Computer Communications and Networks (ICCCN), pp. 1172-1177, 2007.
[7] C Rougier, J Meunier, A St-Arnaud, and J Rousseau, Robust Video Surveillance for Fall Detection Based on Human Shape Deformation, IEEE Transactions on Circuits and Systems for Video Technology (CSVT), Vol. 21, pp. 611-622, 2011
[8] G. Wu, Distinguishing Fall Activities from Normal Activities by Velocity Characteristics, Elsevier Journal of Biomechanics, Vol. 33, pp. 1497-1500, 2000.
[9] Vishwakarma, C. Mandal and S. Sural, Automatic Detection of Human Fall in Video, Springer-Verlag 2nd international conference on Pattern recognition and machine intelligence (PReMI'07), 2007.
[10] R. Cucchiara, A. Prati and R. Vezzani, A Multi-Camera Vision System for Fall Detection and Alarm Generation, Expert Systems Journal, Vol. 24, pp. 334-345, 2007.
[11] Intel open source computer vision library http://www.intel.com/research/mrl/research/opencv.
[12] Bobick and J. Davis. The recognition of human movement using temporal templates. In IEEE Transactions on Pattern Analysis and Machine Intelligence, volume 23, pages 257–267, March 2001.
[13] Lenka Krulikovsk ́a and Jaroslav Polec, “GOP Structure Adaptable to the Location of Shot Cuts”, International Journal of Electronics and Telecommunications, 2012, vol. 58, no. 2, pp. 129–134
[14] Caroline Rougier and Jean Meunier, Alain St-Arnaud, Jacqueline Rousseau,” Fall Detection from Human Shape and Motion History using Video Surveillance”, IEEE International Conference on Advanced Information Networking and Applications Workshops, 2007.
[15] W. H. O. Ageing and L. C. Unit, WHO global report on falls prevention in older age. World Health Organization, 2008.