PiFallD: A Portable Fall Detection System

  • Sanjay Kumar Dhurandher
  • Aubhik Mazumdar
  • Nabeel Khawar
  • Abhisar Garg
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 18)

Abstract

This paper proposes an automated system which can be used to detect when a person has fallen down and alert the concerned immediately, thereby instilling a sense of security in the minds of the elderly and people close to them. The proposed scheme (so-called PiFallD) is designed in the form of a portable, inexpensive and robust fall detection system that is capable of detecting multiple falls and signalling alerts in real time. It utilizes a Raspberry Pi microcontroller and Pi camera, which makes it less expensive. We designed a novel algorithm that efficiently utilizes the system’s limited computing power. Finally, we compared the performance of our system to existing commercial and non-commercial products and discovered that our system handled many problems that have crippled similar systems. We have tested the system in several environments: both outdoors and indoors by creating the PiFallD prototype using a Raspberry Pi 2B+ model installed with a Pi camera REES52. We have performed experiments on the final system and the prototype during development; to imitate all possible conditions, we have tested the system in various environments, indoors and outdoors. It was observed that multiple fall detection was possible and satisfactory. The accuracy of the system was contingent on environment conditions such as lighting and signal strength but still improved on previous work done in this field with a 75% accuracy level in the targeted area of use.

Keywords

Computer vision Motion detection Face detection Internet of things Fall detection Raspberry Pi 

References

  1. 1.
    United Nations, Department of Economic and Social Affairs, Population Division, World Population Ageing Report 2015(ST/ESA/SER.A/390) (2015)Google Scholar
  2. 2.
    H. Axer et al., Falls and gait disorders in geriatric neurology. Clin. Neurol. Neurosurg. 112(4), 265–274 (2010)CrossRefGoogle Scholar
  3. 3.
    M. Alwan, P.J. Rajendran, S. Kell, D. Mack, S. Dalal, M. Wolfe, R. Felder, A smart and passive floor-vibration based fall detector for elderly. Inf. Commun. Technol 1, 1003–1007 (2006).  https://doi.org/10.1109/ICTTA.2006.1684511 CrossRefGoogle Scholar
  4. 4.
    S.V. Mashak, B. hosseini, M. Mokji, Background subtraction for object detection under varying environment, in International Conference of Soft Computing and Pattern Recognition, p. 123–126, December 2010Google Scholar
  5. 5.
    D. DeCarlo, D. Metaxas, The integration of optical flow and deformable models with applications to human face shape and motion estimation, in Proceedings CVPR ’96, pp. 231–238, 1996Google Scholar
  6. 6.
    K. Frba, Real-time face detection using edge-orientation matching: Audio- and video-based biometric person authentication, in 3rd International Conference, AVBPA 2001, Halmstad, Sweden. Proceedings, Springer. ISBN 3-540-42216-1, 2001Google Scholar
  7. 7.
    P. Viola, M.J. Jones, Robust Real-Time Face Detection. Int. J. Comput. Vis 57(2), 127–154 (2004)CrossRefGoogle Scholar
  8. 8.
    T. Mita, T. Kaneko, O. Hori, Joint haar-like features for face detection, in Proceedings of the Tenth IEEE International Conference on Computer Vision, pp. 1550–5499/052, IEEE, 2005Google Scholar
  9. 9.
    K.T. Talele, S.Kadam, A. Tikare, Efficient face detection using adaboost, in IJCA Proceedings on International Conference in Computational Intelligence, 2012Google Scholar
  10. 10.
    H. Weiming, T. Tan, L. Wang, S. Maybank, A survey on visual surveillance of object motion and behaviors. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev 34(3), 334–352 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Sanjay Kumar Dhurandher
    • 1
  • Aubhik Mazumdar
    • 1
  • Nabeel Khawar
    • 1
  • Abhisar Garg
    • 1
  1. 1.CAITFS, Division of Information TechnologyNetaji Subhas Institute of Technology, UniversityofDelhiNew DelhiIndia

Personalised recommendations