The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


A new Framework for Elderly Fall Detection Using Coupled Hidden Markov Models

Falls are a most common problem for old people. They can result in dangerous consequences even death. Many recent works have presented different approaches to detect fall and prevent dangerous outcomes. In this paper, human fall detection from video streams based on a Coupled Hidden Markov Model (CHMM) has been proposed. The CHMM was used to model the motion and static spatial characteristic of human silhouette. The validity of current proposed method was demonstrated with experiments on Le2i database, Weizman database and video from Youtube simulating falls and normal activities. Experimental results showed the superiority of the CHMM for video fall detection.


[1] Ahad M., Tan J., and Kim H., “Motion History Image: its Variants and Applications,” Machine Vision and Applications,vol. 21, no. 6, pp. 1-27, 2010.

[2] Alhimale L., Zedan H., and Al-Bayatti A., “The Implementation of An Intelligent and Video- Based Fall Detection System Using A Neural Network,” Applied Soft Computing, vol. 18, pp. 59-69, 2014.

[3] Alwan M., Rajendran P., Mack D., Dalal S., Wolfe M., and Felder R., “A Smart and Passive °Oor-Vibration Based Fall Detector for Elderly,” in Proceedings of 2nd International Conference on Information and Communication, Damascus, pp. 1003-1007, 2006.

[4] Arshad A., Khan S., Alam A., Ahmad F., and Tasnim R., “A Study on Health Monitoring System: Recent Advancements,” IIUM Engineering Journal, vol. 15, no. 2, pp. 87-99, 2014.

[5] Auvinet E., Multon F., St-Arnaud A., Rousseau J., and Meunier J., “Fall Detection Using Body Volumereconstruction and Vertical Repartition Analysis,” in Proceedings of International Conference on Image and Signalprocessing, Trois-Rivières, pp. 376-383, 2010. (15) 782 The International Arab Journal of Information Technology, Vol. 16, No. 4, July 2019

[6] Charfi I., Mitéran J., Dubois J., Atri M., and Tourki R., “Definition and Performance Evaluation of a Robust SVM Based Fall Detection Solution,” in Proceedings of 8th International Conference on Signal Image Technology and Internet Based Systems, Naples, pp. 218-224, 2012.

[7] Gorelick L., Blank M., Shechtman E., Irani M., and Basri R., http://www.wisdom.weizmann.ac.il/~vision/Sp aceTimeActions.html, Last Visited, 2016.

[8] Hagui M. and Mahjoub M., “Features Selection in Video Fall Detection,” in Proceedings of International Image Processing, Applications and Systems Conference, Sfax, pp. 1-5, 2014.

[9] Hagui M., Mahjoub M., and Ben Amara N., “New Framework for Gait Recognition Using Dynamic Bayesian Model,” in Proceedings of International Conference on Reasoning and Optimization in Information Systems, Sousse, 2013.

[10] Jayech K., Mahjoub M., and Essoukri Ben Amara N.,“Arabic Handwritten Word Recognition Based on Dynamic Bayesian Network,” The International Arab Journal of Information Technology, vol. 13, no. 3, pp. 276-283, 2016.

[11] Kalti K. and Mahjoub M., “Image Segmentation by Gaussian Mixture Models And Modified FCM Algorithm,” The International Arab Journal of Information Technology, vol. 11, no. 1, pp. 11-18, 2014.

[12] Khan M. and Habib H., “Video Analytic for Fall Detection from Shape Features and Motion Gradients,” in Proceedings of the World Congress on Engineering and Computer Science, San Francisco, 2009.

[13] Lim D., Park C., Kim N., Kim S., and Yu Y., “Fall-Detection Algorithm Using 3-Axis Acceleration: Combination with Simple Threshold and Hidden Markov Model,” Journal of Applied Mathematics, vol. 2014, pp. 2-8, 2014.

[14] Luo S. and Hu Q., “A dynamic Motion Pattern Analysis Approach to Fall Detection,” in Proceedings of IEEE International Workshop in Biomedical Circuit and Systems, Singapore, pp. 1-5, 2004.

[15] Mubashir M., Shao L., and Seed L., “A survey on Fall Detection: Principles and Approaches,” Neurocomputing, vol. 100, pp. 144-152, 2013.

[16] Murphy K., “Dynamic Bayesian Networks: Representation,” PhD Thesis, University of California, 2002.

[17] Rougier C., Meunier J., St-Arnaud A., and Rousseau J., “Fall Detection from Human Shape and Motion History using Video Surveillance,” in Proceedings of 21st International Conference on Advanced Information Networking and Applications Workshops, Niagara Falls, pp. 875-880, 2007.

[18] Shih F., Image Processing and Pattern Recognition Fundamentals and Techniques, John Wiley and Sons, 2010.

[19] Stauffer C. and Grimson W., “Adaptive Background Mixture Models for Real-Time Tracking,” in Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, pp. 246-252, 1999.

[20] Thome N. and Miguet S., “A HHMM-Based Approach for Robust Fall Detection,” in Proceedings 9th International Conference on Control, Automation, Robotics and Vision, Singapore, pp. 1-8, 2006.

[21] Tong L., Song Q., Ge Y., and Liu M., “HMM- Based Human Fall Detection and Prediction Method Using Tri-Axial Accelerometer,” IEEE Sensors Journal, vol. 13, no. 5, pp. 1849-1856, 2013.

[22] Trapet A., Fall detection Dataset, http://le2i.cnrs.fr/Fall-detection-Dataset, Last Visited, 2016.

[23] Vishwakarma V., Mandal C., and Sural S., “Automatic Detection of Human Fall in Video,” in Proceedings of International Conference on Pattern Recognition and Machine Intelligence, Kolkata, pp. 616-623, 2007.

[24] Zerrouki N. and Houacine A., “Automatic Classification of Human Body Postures Based on the Truncated SVD,” Journal of Advances in Computer Networks, vol. 2, no. 1, pp. 58-62, 2014.

[25] Zhang M. and Swachuk A., “Context-Aware Fall Detection Using A Bayesian Network,” in Proceedings of the 5th ACM International Workshop on Context-Awareness for Self- Managing Systems, Beijing, pp. 1-6, 2011. A new Framework for Elderly Fall Detection Using Coupled Hidden Markov Models 783 Mabrouka Hagui is phd student at the National Engineering School of Sousse (university of Sousse- Tunisia) and member of research Lab LATIS (Laboratory of Advanced Technology and Intelligent Systems), team signals, images and documents. Mohamed Mahjoub is an associate professor in Signal and Image processing at the National Engineering School of Sousse (university of Sousse - Tunisia) and member of research Lab LATIS (Laboratory of Advanced Technology and Intelligent Systems), team signals, images and documents. His research interests include dynamic bayesian network, computer vision, pattern recognition, HMM and data retrieval. He is a member of IEEE and his main results have been published in international journals and conferences. Faycel ElAyeb received the Ph. D degree in 2012 from National School of Informatic Sciences (University of Manouba-Tunisia). He works currently as an Assistant Professor in Preparatory Institute for Engineering Studies of Monastir. His major research interests are in the field of image analysis and pattern recognition.