A biologically motivated system for unconstrained online learning of visual objects

Authors:
Heiko Wersing;Stephan Kirstein;Michael Götting;Holger Brandl;Mark Dunn;Inna Mikhailova;Christian Goerick;Jochen Steil;Helge Ritter;Edgar Körner
Affiliations:
Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Neuroinformatics Group, Faculty of Technology, Bielefeld University, Bielefeld, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Neuroinformatics Group, Faculty of Technology, Bielefeld University, Bielefeld, Germany;Neuroinformatics Group, Faculty of Technology, Bielefeld University, Bielefeld, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 4
Cited 5

Tracing Patterns and Attention: Humanoid Robot Cognition

IEEE Intelligent Systems
Action Reaction Learning: Automatic Visual Analysis and Synthesis of Interactive Behaviour

ICVS '99 Proceedings of the First International Conference on Computer Vision Systems
Learning optimized features for hierarchical models of invariant object recognition

Neural Computation
Rapid online learning of objects in a biologically motivated recognition architecture

PR'05 Proceedings of the 27th DAGM conference on Pattern Recognition

Adaptive scene dependent filters for segmentation and online learning of visual objects

Neurocomputing
Researching and developing a real-time infrastructure for intelligent systems - Evolution of an integrated approach

Robotics and Autonomous Systems
A biologically motivated visual memory architecture for online learning of objects

Neural Networks
Towards Cognitive Robotics

Creating Brain-Like Intelligence
A robotic game to evaluate interfaces used to show and teach visual objects to a robot in real world condition

Proceedings of the 6th international conference on Human-robot interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a biologically motivated system for object recognition that is capable of online learning of several objects based on interaction with a human teacher. The training is unconstrained in the sense that arbitrary objects can be freely presented in front of a stereo camera system and labeled by speech input. The architecture unites biological principles such as appearance-based representation in topographical feature detection hierarchies and context-driven transfer between different levels of object memory. The learning is fully online and thus avoids an artificial separation of the interaction into training and test phases.