Wrede, Sebastian and Hanheide, Marc and Bauckhage, Christian and Sagerer, Gerhard (2004) An active memory as a model for information fusion. In: International Conference on Information Fusion, June 28 to July 1, 2004, Stockholm, Sweden.

PDF IF04-0198.pdf - Whole Document Restricted to Repository staff only Download (330Kb)

Abstract

Information fusion is a mandatory prerequisite for cognitive vision systems. These are vision systems that apply rea- soning and learning on different levels of abstraction and corre- spondingly have to deal with hypotheses from different categori- cal domains. Following some principles of human cognition, we present an approach to information fusion that closely couples reasoning and representation. We will discuss how processes like probabilistic contextual reasoning as well as functional and non- functional requirements in storing data from different sources can be integrated by a unified XML based data representation. Due to the interaction between active processes and data storage, we call our approach an active memory. Performance results of an implemented system as well as an evaluation of data fusion from contextual inference will be presented.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	Information fusion is a mandatory prerequisite for cognitive vision systems. These are vision systems that apply rea- soning and learning on different levels of abstraction and corre- spondingly have to deal with hypotheses from different categori- cal domains. Following some principles of human cognition, we present an approach to information fusion that closely couples reasoning and representation. We will discuss how processes like probabilistic contextual reasoning as well as functional and non- functional requirements in storing data from different sources can be integrated by a unified XML based data representation. Due to the interaction between active processes and data storage, we call our approach an active memory. Performance results of an implemented system as well as an evaluation of data fusion from contextual inference will be presented.
Keywords:	Robotics, Human-robot interaction, Cognitive Vision, Architecture, Frameworks, Bayesian Networks, XML, Information Fusion, Scene Analysis
Subjects:	H Engineering > H670 Robotics and Cybernetics
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Marc Hanheide
Date Deposited:	23 Nov 2012 17:53
Last Modified:	13 Mar 2013 09:19
URI:	http://eprints.lincoln.ac.uk/id/eprint/6947

Actions (login required)

View Item