| Art der Veröffentlichung: |
Artikel in Konferenzband |
| Autor: |
O. Birbach, J. Kurlbaum, T. Laue, U. Frese |
| Herausgeber: |
Luca Iocchi, Hitoshi Matsubara, Alfredo Weitzenfeld, Changjiu Zhou |
| Titel: |
Tracking of Ball Trajectories with a Free Moving Camera-Inertial Sensor |
| Buch / Sammlungs-Titel: |
RoboCup 2008: Robot Soccer World Cup XII |
| Band: |
5399 |
| Seite(n): |
49 – 60 |
| Serie / Reihe: |
Lecture Notes in Computer Science |
| Erscheinungsjahr: |
2009 |
| Verleger: |
Springer |
| Abstract / Kurzbeschreibung: |
This paper is motivated by the goal of a visual perception
system for the RoboCup 2050 challenge to win against the human worldcup champion. Its contribution is to answer two questions on the subproblem of predicting the motion of a flying ball. First, if we could detect the ball in images, is that enough information to predict its motion precise enough? And second, how much do we lose by using the real-time capable Unscented Kalman Filter (UKF) instead of non-linear maximum likelihood as a gold standard?We present experiments with a camera and an inertial sensor on a helmet worn by a human soccer player. These confirm that the precision is roughly enough and using an UKF is feasible. |
| Internet: |
http://www.informatik.uni-bremen.de/agebv/en/Vision2050 |
| PDF Version: |
http://www.informatik.uni-bremen.de/agebv/downloads/published/birbach_rs_08.pdf |
| Schlagworte: |
sport robotics, robocup, least squares |
| Status: |
Reviewed |
| Letzte Aktualisierung: |
13. 08. 2009 |
