An Approach of Color Object Searching for Vision System of Soccer Robot

Soccer robot system is a perfect platform in research and application of artificial intelligence. It is a feedback control system closed loop by computer vision subsystem. In the vision subsystem, the performances of the veracity and celerity of color object searching influences the performances of the whole system. A color similarity coefficient was proposed to estimate the similarity between two kinds of color in a color image and then adopted in color image object search and segmentation for soccer robot system. That is a novel algorithm for color similarity measurement performed in RGB color space. On the basis of the algorithm, an approach to search color object was also presented. Experimental results show that the approach presented has high precision and speediness for color object searching

[1]  Carla E. Brodley,et al.  Multivariate decision trees , 2004, Machine Learning.

[2]  Rangachar Kasturi,et al.  Machine vision , 1995 .

[3]  Hu Ying Research on Designing of Color Tag and Identifying Algorithm , 2002 .

[4]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[5]  J.-H. Lee,et al.  Comparison of colour transformations for image segmentation , 1994 .

[6]  Manuela M. Veloso,et al.  Fast and inexpensive color image segmentation for interactive robots , 2000, Proceedings. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000) (Cat. No.00CH37113).

[7]  P. Utgoff,et al.  Multivariate Decision Trees , 1995, Machine Learning.

[8]  Wang Wen Crux Techniques of Multi-Agent Robot Soccer System , 2001 .

[9]  Wang Wei ILLUMINATION ADAPTIVE RECOGNITION AND LOCATION SYSTEM FOR UNDERWATER PIPELINE , 2001 .

[10]  Jack Koplowitz,et al.  The weighted nearest neighbor rule for class dependent sample sizes (Corresp.) , 1979, IEEE Trans. Inf. Theory.

[11]  Alan K. Mackworth On Seeing Robots , 1993, Computer Vision: Systems, Theory and Applications.