Illumination Independent Object Recognition

  • Nathan Lovell
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4020)

Abstract

Object recognition under uncontrolled illumination conditions remains one of hardest problems in machine vision. Under known lighting parameters, it is a simple task to calculate a transformation that maps sensed values to the expected colors in objects (and minimize the problems of reflections and/or texture). However, RoboCup aims to develop vision systems for natural lighting conditions in which the conditions are not only unknown but also dynamic. This makes fixed color-based image segmentation infeasible. We present a method for color determination under varying illumination conditions that succeeds in tracking the objects of interest in the RoboCup legged league.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bruce, J., Balch, T., Veloso, M.: Fast and inexpensive color segmentation for interactive robots. In: Int. Conference on Intelligent Robots and Systems. IEEE Computer Society Press, Los Alamitos (2000)Google Scholar
  2. 2.
    Grillo, E., Matteucci, M., Sorrenti, D.G.: Getting the most from your color camera in a color-coded world. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 221–235. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Röfer, T., Brunn, R., Dahm, I., Hebbel, M., Hoffmann, J., Jünge, M., Laue, T.M., Lötzsch, W.N., Spranger, M.: German team 2004 - the german national robocup team. In: Proc. of the Int. Robocup Symposium. Springer, Heidelberg (2004)Google Scholar
  4. 4.
    Dahm, I.: Fully autonomous robot color classification. In: Proc. of the Int. RoboCup Symposium. Springer, Heidelberg (2003)Google Scholar
  5. 5.
    Cameron, D., Barnes, N.: Knowledge-based autonomous dynamic colour calibration. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS, vol. 3020, pp. 226–237. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Dahm, I., Deutsch, S., Hebbel, M.: Robust color classification for robot soccer. In: Proc. of the Int. RoboCup Symposium. Springer, Heidelberg (2003)Google Scholar
  7. 7.
    Jüngel, M., Hoffmann, J., Lötzsch, M.: A real-time auto-adjusting vision system for robotic soccer. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS, vol. 3020, pp. 214–225. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  8. 8.
    Mayer, G., Utz, H., Kraetzschmar, G.K.: Playing robot soccer under natural light: A case study. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS, vol. 3020, pp. 238–249. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  9. 9.
    Sridharan, M., Stone, P.: Towards illumination invariance in the legged league. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 196–208. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  10. 10.
    Steinbauer, G., Bischof, H.: Illumination insensitive robot self-localization using panoramic eigenspaces. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 84–96. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  11. 11.
    Gönner, C., Rous, M., Kraiss, K.-F.: Real-time adaptive colour segmentation for the roboCup middle size league. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 402–409. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  12. 12.
    Lange, S., Riedmiller, M.: Evolution of computer vision subsystems in robot navigation and image classification tasks. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 184–195. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  13. 13.
    Austin, D., Barnes, N.: Red is the new black - or is it? In: Proc. of the 2003 Australasian Conference on Robotics and Automation (2003)Google Scholar
  14. 14.
    Finlayson, G., Hordley, S., Hubel, P.: Colour by correlation: A simple, unifying framework for colour constancy. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11) (2001)Google Scholar
  15. 15.
    Finlayson, G., Hordley, S.: Improving gamut mapping color constancy. IEEE Tranactions on Image Processing 9(10) (2000)Google Scholar
  16. 16.
    Finlayson, G.: Color in perspective. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(10), 1034–1038 (1996)CrossRefGoogle Scholar
  17. 17.
    Brainhard, D., Freeman, W.: Bayesian colour consistency. Journal of Optical Society of America 14(7), 1393–1441 (1986)CrossRefGoogle Scholar
  18. 18.
    Buchsbaum, G.: A spatial processor model for objecct color perception. Journal of Franklin Institute 310, 1–26 (1980)CrossRefGoogle Scholar
  19. 19.
    Murch, C., Chalup, S.: Combining edge detection and colour segmentation in the four-legged league. In: Proc. of the 2003 Australian Robotics and Automation Association (2003)Google Scholar
  20. 20.
    Lovell, N.: Real-time embedded vision system development using aibo vision workshop 2. In: Proc. of the Mexican Int. Conference on Computer Science (2004)Google Scholar
  21. 21.
    Gonzalez, R., Woods, R.: Digital Image Processing. Addison-Wesley, Reading (1992)Google Scholar
  22. 22.
    Chen, J., Chung, E., Edwards, R., Wong, N., Mak, E., Sheh, R., Kim, M., Tang, A., Sutanto, N., Hengst, B., Sammut, C., Uther, W.: rUNSWift team description. In: Proc. of the Int. Robocup Symposium. Springer, Heidelberg (2003)Google Scholar
  23. 23.
    Kaufmann, U., Mayer, G., Kraetzschmar, G.K., Palm, G.: Visual robot detection in roboCup using neural networks. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 262–273. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  24. 24.
    Quinlan, M., Chalup, S., Middleton, R.: Techniques for improving vision and locomotion on the sony aibo robot. In: Proc. of the 2003 Australasian Conference on Robotics and Automation (2003)Google Scholar
  25. 25.
    Estivill-Castro, V., Lovell, N.: Improved object recognition - the robocup 4-legged league. In: Liu, J., Cheung, Y., Yin, H. (eds.) Intelligent Data Engineering and Automated Learning, pp. 1123–1130. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  26. 26.
    Witten, I., Frank, E.: Data Mining — Practical Machine Learning Tools and Technologies with JAVA implementations. Morgan Kaufmann, California (2000)Google Scholar
  27. 27.
    Frank, E., Witten, I.: Generating accurate rule sets without global optimization. In: Machine Learning: Proc. of the Fifteenth Int. Conference. Morgan Kaufmann, San Francisco (1998)Google Scholar
  28. 28.
    Lovell, N., Fenwick, J.: Linear time construction of vectorial object boundaries. In: Hamza, M. (ed.) 6th IASTED Int. Conference on Signal and Image Processing. ACTA Press (2004)Google Scholar
  29. 29.
    Estivill-Castro, V., Fenwick, J., Lovell, N., McKenzie, B., Seymon, S.: Mipal team griffith - team description paper. In: Proc. of the Int. Robocup Symposium. Springer, Heidelberg (2004)Google Scholar
  30. 30.
    Sauer, P.: On the recognition of digital circles in linear time. Computational Geometry: Theory and Applications 2, 287–302 (1993)MATHMathSciNetGoogle Scholar
  31. 31.
    Lovell, N., Estivill-Castro, V.: A descriptive language for flexible and robust object recognition. Springer, Heidelberg (2004)Google Scholar
  32. 32.
    Seysener, C.J., Murch, C.L., Middleton, R.H.: Extensions to object recognition in the four-legged league. In: Nardi, D., Riedmiller, M., Sammut, C., Santos-Victor, J. (eds.) RoboCup 2004. LNCS, vol. 3276, pp. 274–285. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Nathan Lovell
    • 1
  1. 1.School of CITGriffith UniversityNathanAustralia

Personalised recommendations