The application of colour FIRE to robot vision

Abstract

This paper presents a modified FIRE algorithm capable of performing robust edge detection on full colour images. The colour FIRE algorithm is demonstrated on the well known Lena image and comparisons are made with existing edge detection methods. The main application of the colour FIRE presented here is that of robot vision, in particular the application to robot design for the puck collect competition held annually in Vienna, Austria. We show the colour FIRE algorithm to be useful in a robot vision system, giving a good rate of puck classification whist achieving a very low false positive rate.