Neural Robot Detection in RoboCup

13 years 10 months ago

Download www.informatik.uni-ulm.de

Abstract. Improving the game play in RoboCup middle size league requires a fast and robust visual robot detection system. The presented multilevel approach documents, that the combination of a simple color based attention control and a subsequent neural object classiﬁcation can be applied successfully in real world scenarios. The presented results indicate a very good overall performance of this approach.

Gerd Mayer, Ulrich Kaufmann, Gerhard K. Kraetzschm

Real-time Traffic

MIRRORBOT 2005 | Presented Multilevel Approach | RoboCup Middle Size League | Robotics | Subsequent Neural Object |

claim paper

» Velocity Control of an Omnidirectional RoboCup Player with Recurrent Neural Networks

» A Segmentation System for Soccer Robot Based on Neural Networks

» An Adaptive Color Segmentation Algorithm for Sony Legged Robots

» A Constructive Feature Detection Approach for Robotic Vision

» A Vision Based System for GoalDirected Obstacle Avoidance

» Spatiotemporal context in robot vision Detection of static objects in the robocup four leg...

» The Ulm Sparrows 99

» Neural Reinforcement Learning Controllers for a Real Robot Application

Post Info
More Details (n/a)

Added	28 Jun 2010
Updated	28 Jun 2010
Type	Conference
Year	2005
Where	MIRRORBOT
Authors	Gerd Mayer, Ulrich Kaufmann, Gerhard K. Kraetzschmar, Günther Palm

Comments (0)

Sciweavers

Neural Robot Detection in RoboCup

MIRRORBOT 2005 | Presented Multilevel Approach | RoboCup Middle Size League | Robotics | Subsequent Neural Object |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers