Self-organizing Computer Vision for Robust Object Tracking in Smart Cameras

  • Stefan Wildermann
  • Andreas Oetken
  • Jürgen Teich
  • Zoran Salcic
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6407)


Computer vision is one of the key research topics of modern computer science and finds application in manufacturing, surveillance, automotive, robotics, and sophisticated human-machine-interfaces. These applications require small and efficient solutions which are commonly provided as embedded systems. This means that there exist resource constraints, but also the need for increasing adaptivity and robustness. This paper proposes an autonomic computing framework for robust object tracking. A probabilistic tracking algorithm is combined with the use of multi-filter fusion of redundant image filters. The system can react on unpredictable changes in the environment through self-adaptation. Due to resource constraints, the number of filters actively used for tracking is limited. By means of self-organization, the system structure is re-organized to activate filters adequate for the current context. The proposed framework is designed for, but not limited to, embedded computer vision. Experimental evaluations demonstrate the benefit of the approach.


Object Tracking Tracking Result Integral Image Computer Vision System Edge Shape 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fleck, S., Busch, F., Straßer, W.: Adaptive probabilistic tracking embedded in smart cameras for distributed surveillance in a 3d model. Embedded Systems 2007(1), 24–24 (2007)Google Scholar
  2. 2.
    Microsoft’s Project Natal-Homepage,
  3. 3.
    Wolf, W., Ozer, B., Lv, T.: Smart cameras as embedded systems. Computer 35(9), 48–53 (2002)CrossRefGoogle Scholar
  4. 4.
    Rowe, A., Goode, A.G., Goel, D., Nourbakhsh, I.: CMUcam3: An open programmable embedded vision sensor. Technical Report CMU-RI-TR-07-13, Robotics Institute, Pittsburgh, PA (May 2007)Google Scholar
  5. 5.
    Bramberger, M., Brunner, J., Rinner, B., Schwabach, H.: Real-time video analysis on an embedded smart camera for traffic surveillance. In: Proceedings of RTAS 2004, p. 174. IEEE Computer Society Press, Los Alamitos (2004)Google Scholar
  6. 6.
    Wang, G., Salcic, Z., Biglari-Abhari, M.: Customizing multiprocessor implementation of an automated video surveillance system. EURASIP J. Embedded Syst. 2006(1), 1–12 (2006)Google Scholar
  7. 7.
    Johnston, C.T., Gribbon, K.T., Bailey, D.G.: FPGA based remote object tracking for real-time control. In: International Conference on Sensing Technology, pp. 66–72 (2005)Google Scholar
  8. 8.
    Schlessman, J., Chen, C.Y., Wolf, W., Ozer, B., Fujino, K., Itoh, K.: Hardware software co-design of an FPGA-based embedded tracking system. In: Proceedings of CVPRW 2006, p. 123. IEEE Computer Society Press, Los Alamitos (2006)Google Scholar
  9. 9.
    Wildermann, S., Walla, G., Ziermann, T., Teich, J.: Self-organizing multi-cue fusion for FPGA-based embedded imaging. In: Proceedings of FPL 2009, Prague, Czech Republic, pp. 132–137 (2009)Google Scholar
  10. 10.
    Alt, N., Claus, C., Stechele, W.: Hardware software architecture of an algorithm for vision-based real-time vehicle detection in dark environments. In: Proceedings of DATE 2008, pp. 176–181. ACM, New York (2008)Google Scholar
  11. 11.
    Triesch, J., Malsburg, C.V.D.: Democratic integration: Self-organized integration of adaptive cues. Neural Computing 13(9), 2049–2074 (2001)CrossRefzbMATHGoogle Scholar
  12. 12.
    Spengler, M., Schiele, B.: Towards robust multi-cue integration for visual tracking. In: Proceedings of ICVS 2001, pp. 93–106. Springer, Heidelberg (2001)Google Scholar
  13. 13.
    Shen, C., Hengel, A.V.D., Dick, A.: Probabilistic multiple cue integration for particle filter based tracking. In: Proceedings of Digital Image Computing: Techniques and Applications, pp. 10–12 (2003)Google Scholar
  14. 14.
    Arulampalam, S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear non-gaussian bayesian tracking. IEEE Transactions on Signal Processing 50, 174–188 (2002)CrossRefGoogle Scholar
  15. 15.
    Isard, M., Blake, A.: Condensation—conditional density propagation for visual tracking. Journal on Computer Vision 29(1), 5–28 (1998)CrossRefGoogle Scholar
  16. 16.
    Cakar, E., Mnif, M., Müller-Schloer, C., Richter, U., Schmeck, H.: Towards a quantitative notion of self-organisation. In: IEEE Congress on Evolutionary Computation, pp. 4222–4229 (2007)Google Scholar
  17. 17.
    Mühl, G., Werner, M., Jaeger, M.A., Herrmann, K., Parzyjegla, H.: On the definitions of self-managing and self-organizing systems. In: KiVS 2007 Workshop: Selbstorganisierende, Adaptive, Kontextsensitive verteilte Systeme (SAKS 2007), pp. 291–301. VDE Verlag (March 2007)Google Scholar
  18. 18.
    March, J.G.: Exploration and exploitation in organizational learning. Organization Science 2(1), 71–87 (1991)CrossRefGoogle Scholar
  19. 19.
    Vezhnevets, V., Sazonov, V., Andreeva, A.: A survey on pixel-based skin color detection techniques. In: Proceedings of Graphicon, pp. 85–92 (2003)Google Scholar
  20. 20.
    Koch, D., Beckhoff, C., Teich, J.: Recobus-builder a novel tool and technique to build statically and dynamically reconfigurable systems for FPGAs. In: Proceedings of FPL 2008, pp. 119–124 (September 2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Stefan Wildermann
    • 1
  • Andreas Oetken
    • 1
  • Jürgen Teich
    • 1
  • Zoran Salcic
    • 2
  1. 1.University Erlangen-NurembergGermany
  2. 2.The University of AucklandNew Zealand

Personalised recommendations