The evaluation of depth image features for awakening event detection


  • Muhammad Amir As'ari Faculty of Biosciences and Medical Engineering Universiti Teknologi Malaysia 81310 Johor Bahru, Johor, Malaysia
  • Nur Afikah Zainal Abidin
  • Mohd Najeb Jamaludin
  • Lukman Hakim Ismail
  • Hadafi Fitri Mohd Latip



Bedridden, Fall, Depth Image, Machine Learning, Decision Tree


Falls among bedridden would increase in number if they are left unsupervised by the caregivers. The aim of this study is to evaluate the features from the Kinect-like depth image representing the bedridden in detecting the awakening event as the event that falls might occur. The images from 20 subjects performing six sleeping activities including the awakening events were obtained before image segmentation based on horizontal line profile was computed to these images in localizing the bedridden as region of interest. After that, the biggest blob selection was executed in selecting the biggest blob (blob of bedridden person body). Finally, blob analysis was formulated to the resultant image before boxplot and machine learning approach called decision tree were used to analyze the output features of blob analysis. Based on the results from the boxplot analysis, it seems that centroid-x is the most dominant feature to recognize awakening event successfully as the boxplot represent the centroid-x of awakening event were not overlap with other sleeping activities. The result from machine learning approach is also seem in good agreement with boxplot analysis whereby the modelled decision tree with solely using centroid-x achieve the accuracy of 100%. The second largest accuracy is the perimeter followed by major axis length and area.


Nghiem, A. T., Auvinet, E., Meunier, J.) (2012). Head detection using Kinect camera and its application to fall detection. The 11th International Conference on Information Sciences, Dignal Processing and their Applications: Main Tracks. 2-5 July 2012. Canada: IEEE), 1-6.

Barsocchi, P. (2013). Position recognition to support bedsores prevention. IEEE Journal of Biomedical and Health Informatics, 17(1), 53-59.

Hsia, C. C., Liou, K. J., Aung, A. P. W., Foo, V., Huang, W., Biswas, J.) (2009). Analysis and comparison of sleeping posture classification methods using pressure sensitive bed system. 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 3-6 Sept 2009. Minneapolis, Minnesota, USA, 6131-6134.

Lee, C. K., Lee, V. Y. (2013). Fall detection system based on Kinect sensor using novel detection and posture recognition algorithm. International Conference on Smart Homes and Health Telematics. 19-21 June, Singapore, 238-244.

Cheng, G., Kida, S., Furuhashi, H. (2013). Detection of a person awakening or falling out of bed using a range sensor. Information Systems International Conference (ISICO). 2-4 Dec 2013, Bali, Indonesia, 503-508.

Gentleman, R., Huber, W., Carey, V. J. (2008). Supervised machine learning. In Bioconductor case studies. eds. Gentlemen, R., Hornik, K., Parmigiani, G., Springer, New York, 121-136.

Hamid, T. A. T. A. (2015). Population Ageing in Malaysia: A mosaic of Issues, challenges and prospects. Serdang, Malaysia: Penerbit Universiti Putra Malaysia Press.

Knorn, J. & Lindholm, F. (2016). Fall detection using depth maps acquired by a depth sensing camera. Thesis award Master Philosophy, Department of Design Sciences, Lund University, Sweden.

Kim (2012, February 22). The Microsoft Kinect: Advantages and disadvantages [Blog]. Retrieved on 8 October 2016 from http://tkim2012.

Lee, J., Hong, M. and Ryu, S. (2015). Sleep monitoring system using Kinect sensor. International Journal of Distributed Sensor Networks, January 1, 2015, 1-9.

Lim, K. H., Jasvindar, K., Normala, I., Ho, B.K., Yau, W.K., Mohmad, S., Lai, W.Y., Sherina, M.S. (2013). Risk factors of home injury among elderly people in Malaysia. Asian Journal of Gerontology & Geriatrics, 8(2), 1-5.

Martinez, M., Schauerte, B. and Stiefelhagen, R. (Year). “BAM!” Depth-based body analysis in critical care. International Conference on Computer Analysis of Images and Patterns, 27-29 Aug 2013. New York: Springer, 465-472.

Mohamed, A. E. (2017). Comparative study of four supervised machine learning techniques for classification. International Journal of Applied Science and Technology, 7(2), 5-18.

Paarjuli, M., Tran, D., Ma, W., Sharma, D. (2012). Senior health monitoring using Kinect. Fourth International Conference on Communications and Electronics (ICCE). 1-3 Aug 2012, Vietnam, 309-312.

Patsadu, O., Nukoolkit, C., Watanapa , B. (2012). Human gesture recognition using Kinect camera. International Joint Conference on Computer Science and Software Engineering (JCSSE). May 30-June 1 2012. Bangkok, Thailand, 28-32.

Yousefi, R., Ostadabbas, S., Faezipour, M., Farshbaf, M., Nourani, M., Tamil, L. (2011). Bed posture classification for pressure ulcer prevention. 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. August 30 - September 3, 2011. Boston, Massachusetts USA, 7175-7178.

Vilas-Boas, M., Silva, P., Cunha, S. R., Correia, M. V. (2013). Monitoring of bedridden patients: Development of a fall detection tool. 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 3 - 7 July 2013. Osaka, Japan, 1-4.

Wu, H.-H. & Bainbridge-Smith, A. (2011). Advantages of using a Kinect camera in various applications. Electrical & Computer Engineering. University of Canterbury, 1-4.

Li, Y., Berkowitz, L., Noskin, G., Mehrotra, S. (2014). Detection of patient’s bed statuses in 3D using a Microsoft Kinect. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 26-30 August 2014. Chicago, United States, 5900-5903.