Online learning for bootstrapping of object recognition and localization in a biologically motivated architecture

Authors:
Heiko Wersing;Stephan Kirstein;Bernd Schneiders;Ute Bauer-Wersing;Edgar Körner
Affiliations:
Honda Research Institute Europe GmbH, Offenbach/Main, Germany;Technical University of Ilmenau, Ilmenau, Germany;University of Applied Sciences Trier, Birkenfeld, Germany;Univ. of Applied Sciences Frankfurt, Frankfurt, Germany;Honda Research Institute Europe GmbH, Offenbach/Main, Germany
Venue:
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Year:
2008

Citing 6
Cited 1

Learning optimized features for hierarchical models of invariant object recognition

Neural Computation
Learning to Detect Objects in Images via a Sparse, Part-Based Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiclass Object Recognition with Sparse, Localized Features

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Robust Object Recognition with Cortex-Like Mechanisms

IEEE Transactions on Pattern Analysis and Machine Intelligence
The emergence of attention by population-based inference and its role in distributed processing and cognitive control of vision

Computer Vision and Image Understanding - Special issue: Attention and performance in computer vision

Approaches and Challenges for Cognitive Vision Systems

Creating Brain-Like Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a modular architecture for recognition and localization of objects in a scene that is motivated from coupling the ventral ("what") and dorsal ("where") pathways of human visual processing. Our main target is to demonstrate how online learning can be used to bootstrap the representation from nonspecific cues like stereo depth towards object-specific representations for recognition and detection. We show the realization of the system learning objects in a complex realworld environment and investigate its performance.