Using Saliency-Based Visual Attention Methods for Achieving Illumination Invariance in Robot Soccer

Abstract

Abstract. In order to be able to beat the world champion human soccer team in the year 2050, soccer playing robots will need to have very robust vision systems that can cope with drastic changes in illumination conditions. However, the current vision systems are still brittle and they require exhaustive and repeated color calibration procedures to perform acceptably well. In this paper, we investigate the suitability of biologically inspired saliency-based visual attention models for developing robust vision systems for soccer playing robots while focusing on the illumination invariance aspect of the solution. The experiment results demonstrate successful and accurate detection of the ball even when the illumination conditions change continuously and dramatically.

A Fast Method for Adapting Lookup Tables Applied to Changes in Lighting Colour

“…For example when a robot approaches a ball it often ends up in a shadow cast by another robot. Another challenge is that many methods require significant human supervision [11] or substantial computational resources and time [2,12,13]. Only recently more appropriate solutions accessible to small robots such as the DARwIn-OP or Nao have been developed [9].…”