Paper Info
Title
Towards a Calibration-Free Robot: The ACT Algorithm for Automatic Online Color Training
Abstract
Many approaches for object detection based on color coding were published in the RoboCup domain. They are tuned to the typical RoboCup scenario of constant lighting using a static subdivision of the color space. However, such algorithms will soon be of limited use, when playing under changing and finally natural lighting. This paper presents an algorithm for automatic color training, which is able to robustly adapt to different lighting situations online. Using the ACT algorithm a robot is able to play a RoboCup match while the illumination of the field varies.
Year
DOI
Venue
2006
10.1007/978-3-540-74024-7_34
RoboCup 2009
Keywords
Field
DocType
calibration-free robot,different lighting situations online,robocup match,color coding,natural lighting,robocup domain,typical robocup scenario,color space,constant lighting,automatic color training,act algorithm,automatic online color training,look up table,three dimensional,three dimensions
Color space,Computer graphics (images),Computer science,Artificial intelligence,Object detection,Computer vision,Color-coding,Color mapping,Simulation,Algorithm,Subdivision,Robot,Calibration free
Conference
Volume
ISSN
Citations 
4434
0302-9743
11
PageRank 
References 
Authors
1.09
10
4
Name
Order
Citations
PageRank
Patrick Heinemann1454.55
Frank Sehnke252739.18
Felix Streichert320518.20
Andreas Zell41419137.58