Abstract

This paper presents a vision system for robotic soccer which was tested on Sony's four legged robot Aibo. The input for the vision system are images of the camera and the sensor readings of the robot's head joints, the output are the positions of all recognized objects in relation to the robot. The object recognition is based on the colors of the objects and uses a color look-up table. The vision system creates the color look-up table on its own during a soccer game. Thus no prerun calibration is needed and the robot can cope with inhomogeneous or changing light on the soccer field. It is shown, how di#erent layers of color representation can be used to refine the results of color classification.

Citations

155	Fast and inexpensive color image segmentation for interactive robots - Bruce, Balch, et al. - 2000
63	Comparative performance of different skin chrominance models and chrominance space for the automatic detection of human faces in color images - Terrillon, Shirazi, et al.
12	Towards autonomous vision self-calibration for soccer robots - Mayer, Utz, et al. - 2002
10	An algorithm for the rapid computation of boundaries of run length encoded regions - Quek - 2000
9	Knowledge-based autonomous dynamic colour calibration - Cameron, Barnes - 2004
9	Playing robot soccer under natural light: A case study - Mayer, Utz, et al. - 2004
7	Fast Image-based Object Localization in Natural Scenes - Hanek, Schmitt, et al. - 2002