Illumination identification by using image colour data and robot's location and orientation data

Authors:
Michael S. Zehmeister;Yang Sok Kim;Byeong Ho Kang
Affiliations:
School of Computing and Information Systems, University of Tasmania, Sandy Bay, TAS, 7001, Australia.;School of Computing and Information Systems, University of Tasmania, Sandy Bay, TAS, 7001, Australia.;School of Computing and Information Systems, University of Tasmania, Sandy Bay, TAS, 7001, Australia
Venue:
International Journal of Ad Hoc and Ubiquitous Computing
Year:
2009

Citing 4
Cited 0

Fast Image Segmentation, Object Recognition and Localization in a RoboCup Scenario

RoboCup-99: Robot Soccer World Cup III
Structure-based color learning on a mobile robot under changing illumination

Autonomous Robots
Towards illumination invariance in the legged league

RoboCup 2004
Using layered color precision for a self-calibrating vision system

RoboCup 2004

Quantified Score

Hi-index	0.00

Visualization

Abstract

Lighting changes render colour calibrations inaccurate and effectively blind systems that rely on identifying objects by colour. This study investigates the relationships in the colour data of image pixels between lighting conditions in an effort to identify trends that can be used as the basis of a rule-based system. The aim of the system is to identify the current lighting level as one of a set of known conditions. The proposed system uses both the colour data of image pixels and location and orientation information of Artificial Intelligence roBOt (AIBO, homonymous with 'partner' in Japanese) to identify lighting levels, allowing a vision system to switch to an appropriate pre-configured calibration. While the direct area application is on AIBO in the RoboCup domain, the work is applicable in any area that uses color-vision in a situation in which lighting changes occur.