Advertisement

Novel Algorithm on Human Body Fall Detection

  • Kumar Saikat Halder
  • Ashwani SinglaEmail author
  • Ranjit SinghEmail author
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 3)

Abstract

This research work provides a novel algorithm in computer vision for detecting human fall by the help of the trigonometric equation without any sort of machine learning or deep neural networks. Manual monitoring for fall detection can be very expensive as well as time consuming. There are many kinds of research on fall detection recently, but most of them either use wearable sensor technology or machine learning. Very few kinds of research have used image processing technique, where the end result is not much promising. Wearing additional sensors for detecting fall can be uncomfortable for senior citizens. Additionally, machine learning techniques, which requires heavy computational power of computers, might not be financially feasible for massive use, especially residential places. In this research, we have developed an algorithm, that depends on traditional computer vision and trigonometric logic, which requires very less computational power. This is ideal for massive use either for residential use or industrial purposes.

Keywords

Human fall detection Algorithm Computer vision 

Notes

Acknowledgements

We would like to acknowledge project proposer Nasim Hajari (University of Alberta) for providing us with the necessary dataset of fall videos for testing our algorithm and supervised us throughout our research.

References

  1. 1.
    World Health Organization (2007) WHO global report on falls prevention in older age. Switzerland, GenevaGoogle Scholar
  2. 2.
    Bagalà F, Becker C, Cappello A, Chiari L, Aminian K, Hausdorff JM, Zijlstra W, Klenk J (2012) Evaluation of accelerometer-based fall detection algorithms on real-world falls. PloS oneGoogle Scholar
  3. 3.
    Nari MI, Suprapto SS, Kusumah IH, Adiprawita W (2016) A simple design of wearable device for fall detection with accelerometer and gyroscope. Int Symp Electron Smart Devices (ISESD) 2016:88–91CrossRefGoogle Scholar
  4. 4.
    Khojasteh SB, Villar JR, Chira C, González Suárez VM, de la Cal EA (2018) Improving fall detection using an on-wrist wearable accelerometer. SensorsGoogle Scholar
  5. 5.
    Wang CC, Chiang CY, Lin PY, Chou YC, Kuo IT, Huang CN, Chan CT (2008) Development of a fall detecting system for the elderly residents. 2008 2nd international conference on bioinformatics and biomedical engineering: 1359–1362Google Scholar
  6. 6.
    Lindemann U, Hock A, Stuber M, Keck W, Becker C (2005) Evaluation of a fall detector based on accelerometers: a pilot study. Med Biol Eng Comput 43:548–551Google Scholar
  7. 7.
    Bianchi F, Redmond SJ, Narayanan MKR, Cerutti S, Lovell NH (2010) Barometric pressure and triaxial accelerometry-based falls event detection. IEEE Trans Neural Syst Rehabil Eng 18:619–627Google Scholar
  8. 8.
    Abbate S, Avvenuti M, Bonatesta F, Cola G, Corsini P, Vecchio A (2012) A smartphone-based fall detection system. Pervasive and Mob Comput 8:883–899CrossRefGoogle Scholar
  9. 9.
    Mao A, Ma X, He Y, Luo J (2017) Highly portable, sensor-based system for human fall monitoring. SensorsGoogle Scholar
  10. 10.
    Kepski M, Kwolek B (2014) Fall detection using ceiling-mounted 3D depth camera. 2014 international conference on computer vision theory and applications (VISAPP) 2:640–647Google Scholar
  11. 11.
    Rougier C, Meunier JF, St-Arnaud A, Rousseau J (2006) Monocular 3D head tracking to detect falls of elderly people. 2006 international conference of the IEEE engineering in medicine and biology society: 6384–6387Google Scholar
  12. 12.
    Miaou SG, Sung PH, Huang CY (2006) A customized human fall detection system using omni-camera images and personal information. 1st transdisciplinary conference on distributed diagnosis and home healthcare, 2006. D2H2:39–42Google Scholar
  13. 13.
    Liu CL, Lee CH, Lin PM (2010) A fall detection system using k-nearest neighbor classifier. Expert Syst Appl 37:7174–7181.  https://doi.org/10.1016/j.eswa.2010.04.014CrossRefGoogle Scholar
  14. 14.
    Alhimale L, Zedan H, Al-Bayatti AH (2014) The implementation of an intelligent and video-based fall detection system using a neural network. Appl Soft Comput 18:59–69CrossRefGoogle Scholar
  15. 15.
    Qian H, Mao Y, Xiang W, Wang Z (2010) Recognition of human activities using SVM multi-class classifier. Pattern Recogn Lett 31:100–111CrossRefGoogle Scholar
  16. 16.
    Londei ST, Rousseau J, Ducharme FC, St-Arnaud A, Meunier J, Saint-Arnaud J, Giroux F (2009) An intelligent videomonitoring system for fall detection at home: perceptions of elderly people. J Telemedicine and Telecare 15(8):383–90Google Scholar
  17. 17.
    Miguel K de, Brunete A, Hernando M, Gambao E (2017) Home camera-based fall detection system for the elderly. SensorsGoogle Scholar
  18. 18.
    Yoo SG, Oh D (2018) An artificial neural network–based fall detection. Int J Eng Bus Manage 10:184797901878790.  https://doi.org/10.1177/1847979018787905CrossRefGoogle Scholar
  19. 19.
    Leite PJS, Teixeira JMXN, de Farias TSMC, Reis B, Teichrieb V, Kelner J (2011) Nearest neighbor searches on the GPU. Int J Parallel Prog 40:313–330Google Scholar
  20. 20.
    Public dataset “Le2i” for fall detection, link. http://le2i.cnrs.fr/Fall-detection-Dataset?lang=fr
  21. 21.
    Video footage of testing result of our novel algorithm on the public dataset “Le2i” for fall detection, available in https://www.youtube.com/watch?v=yAQU0QzgkVA&feature=youtu.be
  22. 22.
    Suzuki S, Abe K (1985) Topological structural analysis of digitized binary images by border following. Comput Vision, Graphics, and Image Process 30:32–46CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Computing Science, MultimediaUniversity of AlbertaEdmontonCanada

Personalised recommendations