Ontology-based realtime activity monitoring using beam search

Authors:
Wilfried Bohlken;Bernd Neumann;Lothar Hotz;Patrick Koopmann
Affiliations:
FB Informatik, Universität Hamburg, Germany;FB Informatik, Universität Hamburg, Germany;FB Informatik, Universität Hamburg, Germany;FB Informatik, Universität Hamburg, Germany
Venue:
ICVS'11 Proceedings of the 8th international conference on Computer vision systems
Year:
2011

Citing 5
Cited 0

Paradigms of Artificial Intelligence Programming: Case Studies in Common Lisp

Paradigms of Artificial Intelligence Programming: Case Studies in Common Lisp
Video understanding for complex activity recognition

Machine Vision and Applications
Generation of Rules from Ontologies for High-Level Scene Interpretation

RuleML '09 Proceedings of the 2009 International Symposium on Rule Interchange and Applications
Towards an architecture for cognitive vision using qualitative spatio-temporal representations and abduction

Spatial cognition III
Multi-agent event recognition in structured scenarios

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this contribution we present a realtime activity monitoring system, called SCENIOR (SCEne Interpretation with Ontology-based Rules) with several innovative features. Activity concepts are defined in an ontology using OWL, extended by SWRL rules for the temporal structure, and are automatically transformed into a high-level scene interpretation system based on JESS rules. Interpretation goals are transformed into hierarchical hypotheses structures associated with constraints and embedded in a probabilistic scene model. The incremental interpretation process is organised as a Beam Search with multiple parallel interpretation threads. At each step, a context-dependent probabilistic rating is computed for each partial interpretation reflecting the probability of that interpretation to reach completion. Low-rated threads are discarded depending on the beam width. Fully instantiated hypotheses may be used as input for higher-level hypotheses, thus realising a doubly hierarchical recognition process. Missing evidence may be "hallucinated" depending on the context. The system has been evaluated with real-life data of aircraft service activities.