Research on Color Feature Selection Using Genetic Algorithm in Robot Soccer

Abstract:

Feature selection is a hot topic in the field of pattern recognition. In this paper, we present a new feature selection algorithm which is used on the soccer robot MT-R for the ball recognition. The illumination invariant color feature set is defined based on the dichromatic reflection. By means of genetic algorithm we determine the most discriminating color feature subset. Experimental results show that the proposed color feature subset achieves high object recognition accuracy.

• Periodical: Advanced Materials Research (Volume 505)
• Pages: 311-316
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.505.311
• Online since: April 2012
• Authors: Xin Luan, Ming Chen, Zheng Yuan Sun, Da Lei Song, Lei Hua Ge, Li Wang
• Keywords: Feature Selection, Feature Subsets, Genetic Algorithm (GA), Robot Soccer

References

[1] D. Koller, M. Sahami, "Toward Optimal Feature Selection[A]," Proc of Int'l Conf on Machine Learning[C].1966, pp.284-292.

[2] B.Chakraborty, "Genetic Algorithm with Fuzzy Fitness Function for Feature Selection[A]," Proc of the 2002 IEEE Int'1 Symp on Industrial Electronics. Vol 1[C].2002, pp.315-319.

DOI: 10.1109/isie.2002.1026085

[3] S.B. Serpico, L. Bruzzone, "A new search algorithm for feature selection in hyper spectral remote sensing images[J]," IEEE Trans on Geoscience and Remote Sensing, 2001,39(7), pp.1360-1367.

DOI: 10.1109/36.934069

[4] Xin Luan, Wei-Wei Qi and Da-Lei Song, "Illumination Invariant Color Model for Object Recognition in Robot Soccer," Lecture Notes in Computer Science, v 6146 LNCS, n PART, pp.680-687,2010.

DOI: 10.1007/978-3-642-13498-2_89

[5] Li Jin-zong, Zhang Ze-xu, Wei Xiang-quan and Wang Yu-hui, "Research of color constancy based on dichromatic reflection model," in jouranl of system simulation, vol.13, Nov,2001, pp.148-155.

[6] A. Neves, G.Corrente and A.Pinho, "An omnidirectional vision system for soccer robots," Progress in artificial intelligence.Lecture notes in artificial intelligenc, vol, 4874. Springer, 2007,pp.499-507.

DOI: 10.1007/978-3-540-77002-2_42

[7] Kobus Barnard, "Modeling scene illumination color for computer vision and image reproduction: A survey of computational approaches[D]." SFU phD depth paper, December 1998.

[8] Zhao Yun and Liu Weiyi, "Research on feature selection using genetic algorithms," in Computer engineering and application, vol.15, 2004,pp.52-54.

[9] Jia Wenjing, Zhang Huaifeng, He Xiangjian, Wu Qiang, C. "A comparison on histogram based image matching methods." In: IEEE International Conference on Video and Signal Based Surveillance, page 97,2006.

DOI: 10.1109/avss.2006.5

[10] C.R. Houck, J.Joines and M. Kay, "A genetic algorithm for function optimisation: A Matlab implemmentation," ACM Transactions on Mathematical Software, 1996.

[11] M.S. Shyu, "A genetic algorithm approach to color image enhancement." Master thesis, Institute of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan, Republic of China(1995).

[12] Sridharan. Mohan. "Autonomous color learning on a mobile robot." Proceedings of the National Conference on Artificial Intelligence, v 3, pp.1318-1323,(2005)