High-Level Expectations for Low-Level Image Processing

Authors:
Lothar Hotz;Bernd Neumann;Kasim Terzic
Affiliations:
HITeC e.V. c/o Department Informatik, Universität Hamburg, Hamburg, Germany 22527;Cognitive Systems Laboratory, Department Informatik, Universität Hamburg, Hamburg, Germany 22527;Cognitive Systems Laboratory, Department Informatik, Universität Hamburg, Hamburg, Germany 22527
Venue:
KI '08 Proceedings of the 31st annual German conference on Advances in Artificial Intelligence
Year:
2008

Citing 9
Cited 3

On the use of motion concepts for top-down control in traffic scenes

ECCV 90 Proceedings of the first european conference on Computer vision
Expectation-based dynamic scene understanding

Active vision
Natural Language Description of Image Sequences as a Form of Knowledge Representation

KI '99 Proceedings of the 23rd Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Contextual Coordination in a Cognitive Vision System for Symbolic Activity Interpretation

ICVS '06 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems
A Real-Time Scene Understanding System for Airport Apron Monitoring

ICVS '06 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems
Evaluation and Knowledge Representation Formalisms to Improve Video Understanding

ICVS '06 Proceedings of the Fourth IEEE International Conference on Computer Vision Systems
Learning a Knowledge Base of Ontological Concepts for High-Level Scene Interpretation

ICMLA '07 Proceedings of the Sixth International Conference on Machine Learning and Applications
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
Navigating through logic-based scene models for high-level scene interpretations

ICVS'03 Proceedings of the 3rd international conference on Computer vision systems

Trends and issues in description logics frameworks for image interpretation

SETN'10 Proceedings of the 6th Hellenic conference on Artificial Intelligence: theories, models and applications
Model-based recognition of 2D objects under perspective distortion

Pattern Recognition and Image Analysis
Beyond physical product configuration --Configuration in unusual domains

AI Communications - Intelligent Engineering Techniques for Knowledge Bases

Quantified Score

Hi-index	0.00

Visualization

Abstract

Scene interpretation systems are often conceived as extensions of low-level image analysis with bottom-up processing for high-level interpretations. In this contribution we show how a generic high-level interpretation system can generate hypotheses and initiate feedback in terms of top-down controlled low-level image analysis. Experimental results are reported about the recognition of structures in building facades.