On scene interpretation with description logics

DMCA

On scene interpretation with description logics (2006)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Bernd Neumann , Ralf Möller , Technische Universität Hamburg-harburg

Venue:	Cognitive Vision Systems, volume 3948 of LNCS
Citations:	88 - 22 self

BibTeX

@INPROCEEDINGS{Neumann06onscene,
    author = {Bernd Neumann and Ralf Möller and Technische Universität Hamburg-harburg},
    title = {On scene interpretation with description logics},
    booktitle = {Cognitive Vision Systems, volume 3948 of LNCS},
    year = {2006},
    pages = {247--275},
    publisher = {Springer}
}

OpenURL

Abstract

We examine the possible use of Description Logics as a knowledge representation and reasoning system for high-level scene interpretation. It is shown that aggregates composed of multiple parts and constrained primarily by temporal and spatial relations can be used to represent high-level concepts such as object configurations, occurrences, events and episodes. Scene interpretation is modelled as a stepwise process which exploits the taxonomical and compositional relations between aggregate concepts while incorporating visual evidence and contextual information. It is shown that aggregates can be represented by a Description Logic ALCF(D) which provides feature chains and a concrete domain extension for quantitative temporal and spatial constraints. Reasoning services of the DL system can be used as building blocks for the interpretation process, but additional information is required to generate preferred interpretations. A probabilistic model is sketched which can be integrated with the knowledge-based framework. 1.

Keyphrases

description logic scene interpretation dl system high-level concept interpretation process description logic alcf knowledge-based framework preferred interpretation spatial relation building block reasoning system possible use contextual information aggregate concept compositional relation stepwise process spatial constraint feature chain knowledge representation object configuration visual evidence multiple part concrete domain extension high-level scene interpretation probabilistic model additional information

DMCA