Preventing Drowning Accidents Using Thermal Cameras

  • Soren Bonderup
  • Jonas OlssonEmail author
  • Morten Bonderup
  • Thomas B. Moeslund
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10073)


Every year approximately 372 000 people die from unintentional drowning, causing it to be a top-3 cause to unintentional injury [1]. In Denmark 25% of drownings happen at harbor areas [2]. To address this problem thermal cameras have been placed strategically at a harbor. Using computer vision techniques an automatic surveillance system for predicting and detecting drowning accidents has been implemented. First a person detector has been implemented using simple human characteristics. The person is tracked using a Kalman Filter. Using the tracker as a prior, a fall prediction is determined. A fall detector is implemented using a virtual trip-wire in combination with an optical flow algorithm making the system able to detect 100% of all falls and only yielding a 0.08 false positive rate hourly. The entire system has been developed using 155 h of real life thermal video, hereof 56 h are manually annotated.


  1. 1.
    World Health Organization, et al.: Global report on drowning: preventing a leading killer. World Health Organization (2014)Google Scholar
  2. 2.
    Syddansk Universitet, Statens Institut for Folkesundhed: Drukneddsfald i danmark 2001–2013. (2015)Google Scholar
  3. 3.
    Wallace, E., Diffley, C.: CCTV: making it work. Police Scientific Development Branch of the Home Office (PSDB) Publication 14, 98 (1998)Google Scholar
  4. 4.
    Poseidon Technologies Inc.: Poseidon (2016).
  5. 5.
    Eng, H.L., Toh, K.A., Kam, A.H., Wang, J., Yau, W.Y.: An automatic drowning detection surveillance system for challenging outdoor pool environments. In: Proceedings of the Ninth IEEE International Conference on Computer Vision, pp. 532–539. IEEE (2003)Google Scholar
  6. 6.
    Gade, R., Moeslund, T.B.: Thermal cameras and applications: a survey. Mach. Vis. Appl. 25, 245–262 (2014)CrossRefGoogle Scholar
  7. 7.
    Wong, W.K., Tan, P.N., Loo, C.K., Lim, W.S.: An effective surveillance system using thermal camera. In: International Conference on Signal Acquisition and Processing, ICSAP 2009, pp. 13–17. IEEE (2009)Google Scholar
  8. 8.
    Conaire, Ó., C., O’Connor, N.E., Cooke, E., Smeaton, A.F.: Comparison of fusion methods for thermo-visual surveillance tracking. Institute of Electrical and Electronics Engineers (2006)Google Scholar
  9. 9.
    Torabi, A., Massé, G., Bilodeau, G.A.: An iterative integrated framework for thermal-visible image registration, sensor fusion, and people tracking for video surveillance applications. Comput. Vis. Image Underst. 116, 210–221 (2012)CrossRefGoogle Scholar
  10. 10.
    Wong, W.K., Hui, J.H., Loo, C.K., Lim, W.S.: Off-time swimming pool surveillance using thermal imaging system. In: 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA), pp. 366–371. IEEE (2011)Google Scholar
  11. 11.
    Hikvision: Safety and reliable detection for critical infrastructure, Hikvision dual lens thermal cameras. Web (2015)Google Scholar
  12. 12.
    Harney, R.C.: COMBAT SYSTEMS, vol. 1. Sensor Elements Part I. Sensor Functional Characteristics (2004)Google Scholar
  13. 13.
    Vahora, S., Chauhan, N., Prajapati, N.: A robust method for moving object detection using modified statistical mean method. Int. J. Adv. Inf. Technol. 2, 65 (2012)CrossRefGoogle Scholar
  14. 14.
    KaewTraKulPong, P., Bowden, R.: An improved adaptive background mixture model for real-time tracking with shadow detection. In: Remagnino, P., Jones, G.A., Paragios, N., Regazzoni, C.S. (eds.) Video-Based Surveillance Systems, pp. 135–144. Springer, New York (2002)CrossRefGoogle Scholar
  15. 15.
    Szwoch, G., Szczodrak, M.: Detection of moving objects in images combined from video and thermal cameras. In: Dziech, A., Czyżewski, A. (eds.) MCSS 2013. CCIS, vol. 368, pp. 262–272. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-38559-9_23 CrossRefGoogle Scholar
  16. 16.
    Gade, R., Jørgensen, A., Moeslund, T.B.: Occupancy analysis of sports arenas using thermal imaging. In: International Conference on Computer Vision Theory and Applications, pp. 277–283 (2012)Google Scholar
  17. 17.
    Ericson, C.: Real-Time Collision Detection. CRC Press, Boca Raton (2004)Google Scholar
  18. 18.
    Kuhn, H.W.: The hungarian method for the assignment problem. Naval Res. Logistics Q. 2, 83–97 (1955)MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Farnebäck, G.: Two-frame motion estimation based on polynomial expansion. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 363–370. Springer, Heidelberg (2003). doi: 10.1007/3-540-45103-X_50 CrossRefGoogle Scholar
  20. 20.
    Cassidy, D., Holton, G., Rutherford, F.: Understanding Physics. Undergraduate Texts in Contemporary Physics. Springer, New York (2002)CrossRefzbMATHGoogle Scholar
  21. 21.
    Baldonado, M., Chang, C.C., Gravano, L., Paepcke, A.: The stanford digital library metadata architecture. Int. J. Digit. Libr. 1, 108–121 (1997)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Soren Bonderup
    • 1
  • Jonas Olsson
    • 1
    Email author
  • Morten Bonderup
    • 1
  • Thomas B. Moeslund
    • 1
  1. 1.University of AalborgAalborgDenmark

Personalised recommendations