Combining Pattern Matching and Optical Flow Methods in Home Care Vision System

  • Zbigniew Mikrut
  • Przemysław Pleciak
  • Magdalena Smoleń
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7339)


The article presents the structure and working of the system supervising the convalescent or elder person at home. Images acquired from a suitably mounted camera are analyzed to determine the pose and activity of the observed person. Extensive configuration module allows to define zones of rest and obstructing objects. Situations of long immobility are detected in places where it should not happen. The activity of observed person is computed using two independent methods: by counting the number of frames in which the active poses are detected and by counting the number of frames, in which the dominant component of the optical flow histogram exceeded the threshold value. By keeping methods of image analysis as simple as possible the processing time was achieved close to the real-time.


home care system optical flow remote surveillance system 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Buccolieri, F., Distante, C., Leone, A.: Human posture recognition using active contours and radial basis function neural network. IEEE Advanced Video and Signal Based Surveillance, 213–218 (2005), doi:10.1109/AVSS.2005.1577269Google Scholar
  2. 2.
    Chen S., Folowosele F., Kim D., Vogelstein R.J., Etienne-Cummings, R., Culurciello, E.: A size and position invariant event-based human posture recognition algorithm. IEEE Biomedical Circuits and Systems Conference, doi: 10.1109/BIOCAS.2008.4696930, pp. 285–288 (2008).Google Scholar
  3. 3.
    Fleet, D.J., Weiss, Y.: Mathematical Models in Computer Vision. The Handbook, Optical Flow Estimation, ch. 15, pp. 239–258. Springer (2005)Google Scholar
  4. 4.
    Goldman, L., Karaman, M., Sikora, T.: Human body posture recognition using MPEG-7 descriptors. In: Proc. SPIE 5308, vol. 177 (2004), doi:10.1117/12.526666Google Scholar
  5. 5.
    Martinez J. M.: MPEG-7 Overview (2004),
  6. 6.
    Mikrut, Z., Smoleń, M.: A neural network approach to recognition of the selected human motion patterns. Automatyka 15(3), 535–543 (2011)Google Scholar
  7. 7.
    Rowe, D.: Towards robust multiple-target tracking in unconstrained human-populated environments. In: Reviewing Detections and Tracking Approaches, ch. 2, Universitat Autonoma de Barcelona, Spain (2008)Google Scholar
  8. 8.
    Tadeusiewicz, R.: Place and role of intelligent systems in computer science. Computer Methods in Materials Science 10(4), 193–206 (2010)Google Scholar
  9. 9.
    Vezzani, R., Baltieri, D., Cucchiara, R.: HMM Based Action Recognition with Projection Histogram Features. In: Ünay, D., Çataltepe, Z., Aksoy, S. (eds.) ICPR 2010. LNCS, vol. 6388, pp. 286–293. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  10. 10.
  11. 11.

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Zbigniew Mikrut
    • 1
  • Przemysław Pleciak
    • 1
  • Magdalena Smoleń
    • 1
  1. 1.AGH University of Science and TechnologyKrakówPoland

Personalised recommendations