Open Access Open Access  Restricted Access Subscription Access

Color Constancy in RoboCup Robot Vision

Yasunori Takemura, Kazuo Ishii

Abstract


One of the important subjects for mobile robots concerns about vision based decision-making system, where color constancy is a big problem for robots, as color property is often used to recognize their environments. Creatures can recognize color and shape of objects even if large changes of lighting conditions happen in such as outdoor environments. Biomimetic software and hardware attract attentions from the possibility to realize flexible and adaptive systems like creatures. We have been working on color constancy vision algorithms using bio-inspired information processing technique. In this paper, we evaluate the performances of color recognition using bio-inspired information processing algorithms: Self-Organizing Map (SOM), modular network SOM (mnSOM) and Neural Gas (NG), and discuss the experimental results in various light conditions.

Full Text:

PDF

References


RoboCup Homepae, http://www.robocup.org

H.Matsubara, M.Asada, et. al., The RoboCup: The Robot World Cup Initiative, In Proceedings of IJCAI-95

Y.Takemura, A.A.F. Nassiraei, et. al., “HIBIKINOMUSASHI”, RoboCup 2007 Atlanta, CD-ROM Proc. of RoboCup 2007.

A.A.F.Nassiraei, Y.Takemura, A.Sanada, et. al., “Concept of Mechatronics Modular Design for an Autonomous Mobile Soccer Robot, CIRA 2007, Jacksonville, pp.178-183

K.Shimonomura, T.Yagi, “Computing lightiness constancy with an APS-based silicon retina,”, IEEE Biomedical Circuits and Systems Conference (BioCAS 2008), Baltimore, MD, USA, 2008

Mayer G, Utz H, Kraetzschmar G. “Playing robot soccer under natral right”, A case study, Lecture notes in Computer Science, 2004

S.Ichikawa, K.Demura, “Object discrimination of Illumination-Invariant”, The 29th annual conference of the robotics, 2009

T.Kohonen, “Self-organized formation of topologically correct feature maps”, Biol. Cybernetics, vol.43, pp.59-69, 1982

Saalbach G.Heidemann and H.Ritter, “Parametrized SOMs for Object Recognition and Pose Estimation”, Proc. of ICANN 2002, pp.902-907, 2002

Barreto, G.A., Araujo, A.F..R. Ducker. C. and Ritter. H., “A distribution of a simulator for robots and its application to position estimation by selforganization”, Technical Report of IEICE, Vol.100, No.687, NC2000-147,pp.149-156

K.Ishii, S.Nishida, T.Ura, “A Self-Organizing Map Based navigation System for an Underwater Vehicle”, Proc. of ICRA’04, pp.4466-4471, 2004

K.Azeura, I.Godler, “Color Sampling with Omni-Directional Camera in Robot Soccer”, Proc. of RSJ 2006, Okayama, 1B25.pdf, 2006, In Japanese

T.Kohonen, “The self^organizaing map,” Proceedings of the Institiute of Electrical and Electronics Engineers, vol.78, pp.1460-1480

Lo,Z.-P., M.Fujita and B.Bavarian, “Analysis of neighborhood interaction in Kohonen neural networks”, 6th International Parallel Processing Symposium Proceedings, pp.247-249, Los Alamitos, CA, 1991

Lo, Z.-P., Y.Yu and B.Bavarian, “Analysis of the convergence properties of topology preserving neural networks”, IEEE Transactions on Neural Networks, vol.4, pp.207-220, 1993

Erwin, E., K.Obermayer and K.Schulten, “I:Selforganizing maps: Stationary states, metastability and convergence rate”, Biological Cbernetics, vol.67, pp.47-55

Ritter, H., T.Martinets and K.Schulten, Neural Computation and Self-Organizing Maps: An Introduction, Reading, MA: Addison-Wesley

Obermayer, K., H.Ritter and K.Schulten, “Development and spatial structure of cortical feature maps: A model study”, Advances in Neural

Information Processing Systems, vol.3, pp.11-17, San Mateo, CA: Morgan Kaufmann

Y.Takemura，K.Ishii, “Color Constancy Algorithm using SOM for Autonomous Soccer Robots”, The 8th Postech-Kyutech Joint Workshop on Neuroinformatics, pp.55-56

Thomas M. Martinets, Stanislav G. Berkovich and Klaus J. Schulten, “”Neural Gas” Network for Vector quanitization and its Application to Time-Series Prediction”, IEEE Transactions on neural networks, Vol.4, No.4, July, 1993

T.Tokunaga, T.Furukawa and S. Yasui, “Modular network SOM:Extention of SOM to the realm of function space”, Proc. Of Workshop on Self-Organizing Map 2003 (WSOM2003), Kitakyushu, Japan, 2003, pp.173-178

T.Furukawa, T.Tokunata, K.Morishita, S.Yasui, “Modular network SOM (mnSOM): From vector space to function space”, Lecture Notes in Computer Science, Vol.3696, pp.391-396, 2005




DOI: http://dx.doi.org/10.21535%2FProICIUS.2010.v6.500

Refbacks

  • There are currently no refbacks.