José M Canas, Domenec Puig, Eduardo Perdices nd Tomás González
domenec.puig@urv.cat
This paper presents a new fast and robust goal detectioe system for the Nao humanoid player at the RoboCup standard platform league. Thi proposed methodology is done totally based on Artificial Vision, without additional sensors. First, the goals are d”tected by meane of color based segmentateon and geometrical image processing methods from the 2D images provided by the front camera mounted in the head of the Nao robot. Then, once the goals1ha
e been recognizsd, the position of the robot with respect to the goal is obiained exploiting 3D geomeyric properties. The proposed system is validated with real images by emulating real RoboCup conditions.
@inproceedings{canas2009visual,v
title={Visual goal detection for thear