Towards Illumination Invariance in the Legged League
To date, RoboCup games have all been played under constant, bright lighting conditions. However, in order to meet the overall goal of RoboCup, robots will need to be able to seamlessly handle changing, natural light. One method for doing so is to be able to identify colors regardless of illumination: color constancy. Color constancy is a relatively recent, but increasingly important, topic in vision research. Most approaches so far have focussed on stationary cameras. In this paper we propose a methodology for color constancy on mobile robots. We describe a technique that we have used to solve a subset of the problem, in real-time, based on color space distributions and the KL-divergence measure. We fully implement our technique and present detailed empirical results in a robot soccer scenario.
KeywordsIllumination invariance Color constancy KL-divergence mobile robots
Unable to display preview. Download preview PDF.
- 1.The International RoboSoccer Competition, http://www.robocup.org
- 2.The Sony Aibo robots, http://www.us.aibo.com
- 7.Finlayson, G., Hordley, S.: Improving gamut mapping color constancy. IEEE Transactions on Image Processing 9(10) (October 2000)Google Scholar
- 8.Finla yson, G., Hordley, S., Hub el, P.: Color by correlation: A simple, unifying framework for color constancy. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(11) (November 2001)Google Scholar
- 11.Kitano, H., Asada, M., Kuniyoshi, Y., Noda, I., Osawa, E.: Robocup:the robot world cup initiative. proceedings of the first international conference on autonomous agents. In: Proceedings of the International Conference of Robotics and Automation, pp. 340–347 (February 1997)Google Scholar
- 12.Land, E.H.: The retinex theory of color constancy. Scientific American, 108–129 (1977)Google Scholar
- 13.Lenser, S., Veloso, M.: Automatic detection and response to environmental change. In: Proceedings of the International Conference of Robotics and Automation (May 2003)Google Scholar
- 15.Rosenberg, C., Hebert, M., Thrun, S.: Color constancy using kl-divergence. In: IEEE International Conference on Computer Vision (2001)Google Scholar
- 16.Sridharan, M., Stone, P.: Towards illumination invariance on mobile robots. In: The First Canadian Conference on Computer and Robot Vision (2004)Google Scholar
- 17.Stone, P., Dresner, K., Erdoğan, S.T., Fidelman, P., Jong, N.K., Kohl, N., Kuhlmann, G., Lin, E., Sridharan, M., Stronger, D., Hariharan, G.: Ut austin villa 2003: A new robocup four-legged team, ai technical report 03-304. Technical report, Department of Computer Sciences, University of Texas at Austin (October 2003)Google Scholar
- 18.Thrun, S., Fox, D., Burgard, W., Dellaert, F.: Robust monte carlo localization for mobile robots. Journal of Artificial Intelligence (2001)Google Scholar
- 19.Tsin, Y., Collins, R.T., Ramesh, V., Kanade, T.: Bayesian color constancy for outdoor object recognition. IEEE Pattern Recognition and Computer Vision (December 2001)Google Scholar