Signal, Image and Video Processing

, Volume 9, Issue 3, pp 623–633 | Cite as

A simple vision-based fall detection technique for indoor video surveillance

  • Jia-Luen Chua
  • Yoong Choon Chang
  • Wee Keong Lim
Original Paper


Falls are one of the major health hazards among the aging population aged 65 and above, which could potentially result in a significant hindrance to their independent living. With the advances in medical science in the last few decades, the aging population increases every year, and thus, fall detection system at home is increasingly important. This paper presents a new vision-based fall detection technique that is based on human shape variation where only three points are used to represent a person instead of the conventional ellipse or bounding box. Falls are detected by analyzing the shape change of the human silhouette through the features extracted from the three points. Experiment results show that in comparison with the conventional ellipse and bounding box techniques, the proposed three point–based technique increases the fall detection rate without increasing the computational complexity.


Fall detection Analysis of human shape variation computer vision 

List of Symbols


Height of the bounding box


Width of the bounding box


Height of region \(R1\)


Height of region \(R2\)


Height of region \(R3\)


Width of region \(R1\)


Width of region \(R2\)


Width of region \(R3\)

\((g_{R1x},\, g_{R1y})\)

Centroid coordinate of region \(R1\)

\((g_{R2x},\, g_{R2y})\)

Centroid coordinate of region \(R2\)

\((g_{R3x},\, g_{R3y})\)

Centroid coordinate of region \(R3\)


Distance between \(P1\) and \(P2\)


Distance between \(P2\) and \(P3\)

\(\theta _{1}\)

Orientation of the line formed by \(P1\) and \(P2\)

\(\theta _{2}\)

Orientation of the line formed by \(P2\) and \(P3\)


Ratio of the distance \(D1\) over \(D2\)


Ratio of the distance at previous frame


Ratio of the distance at current frame

\(\theta _{r}\)

Reference angle


Length reference

\(\theta _{N1}\)

Orientation of the line formed by \(P1\) and \(P2\) at the 10th frame after a possible fall

\(\theta _{N2}\)

Orientation of the line formed by \(P2\) and \(P3\) at the 10th frame after a possible fall

\(\theta _{D1}\)

Orientation difference between \(\theta _{N1}\) and \(\theta _{r}\)

\(\theta _{D2}\)

Orientation difference between \(\theta _{N2}\) and \(\theta _{r}\)

\(\mu _{\theta }\)

Mean of the two orientation differences, \(\theta _{D1}\) and \(\theta _{D2}\)


Change in sum of the length of the lines after a possible fall



This work was supported in part by Telekom Malaysia Research and Development (TM R&D) research grant.

Conflict of interest The authors declare that they have no competing interests.


  1. 1.
    Hausdorff, J.M., Rios, D.A., Edelber, H.K.: Gait variability and fall risk in community-living older adults: a 1-year prospective study. Arch. Phys. Med. Rehabil. 82(8), 1050–1056 (2001)CrossRefGoogle Scholar
  2. 2.
    Population Statistics in Malaysia. Department of Statistic Malaysia [Online]. Available: (2010)
  3. 3.
    Hashim, A.: Overview of Malaysia’s Integrated Telehealth Project. The International Medical Journal. [Online]. Available: (2003)
  4. 4.
    World Population Ageing. United Nations, New York [Online]: Available: (2009)
  5. 5.
    Falls among Older Adults: An Overview. Web-based Injury Statistics Query and Reporting System (Centers for Disease Control and Prevention, National Center for Injury Prevention and Control). [Online]. Available: Accessed 11 March 2011
  6. 6.
    Willems, J., Debard, G., Bonroy, B., Vanrumste, B., Goedemé, T.: How to detect human fall in video? An overview. In: International Conference on Positioning and Context-Awareness, Antwerp Belgium, May 2009Google Scholar
  7. 7.
    Nguyen, T.-T., Cho, M.-C., Lee, T.-S.: Automatic fall detection using wearable biomedical signal measurement terminal. In: Proceedings of 31st Annual International Conference of the IEEE EMBS, pp. 5203–5206 (2009)Google Scholar
  8. 8.
    Rougier, C., Meunier, J., St-Arnaud, A., Rousseau, J.: Robust video surveillance for fall detection based on human shape deformation. IEEE Trans Circuits Syst. Video Technol. 21(5), 611–622 (2011)Google Scholar
  9. 9.
    Cucchiara, R., Prati, A., Vezzani, R.: A multi-camera vision system for fall detection and alarm generation. Expert Syst J 24(5), 334–345 (2007) Google Scholar
  10. 10.
    Williams, A., Ganesan, D., Hanson, A.: Aging in place: fall detection and localization in a distributed smart camera network. In: Proceedings of the 15th international conference on Multimedia, pp. 892–901 (2007)Google Scholar
  11. 11.
    Vishwakarma, V., Mandal, C., Sural, S.: Automatic detection of human fall in video. Lect. Notes Comput. Sci. Patt. Recogn. Mach. Intell. 4815, 616–623 (2007)CrossRefGoogle Scholar
  12. 12.
    Tao, J., Turjo, M., Wong, M. F., Wang, M., Tan, Y. P.: Fall incidents detection for intelligent video surveillance. In: Proceedings of IEEE International Conference on Communication and Signal Processing, pp. 1590–1594 (2005)Google Scholar
  13. 13.
    Rougier, C., Meunier, J., St-Arnaud, A., Rousseau, J.: Fall detection from human shape and motion history using video surveillance. Proc. 21st Int. Conf. AINAW 2, 875–880 (2007)Google Scholar
  14. 14.
    Chen, Y.T., Lin, Y.C., Fang, W.H.: A hybrid human fall detection scheme. In: Proceedings of 2010 IEEE 17th International Conference on Image Processing, pp. 3485–3488 (2010)Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  • Jia-Luen Chua
    • 1
  • Yoong Choon Chang
    • 1
  • Wee Keong Lim
    • 1
  1. 1.Faculty of EngineeringMultimedia UniversityCyberjayaMalaysia

Personalised recommendations