Detecting events in video data using a formal ontology of motion verbs

  • Authors:
  • Tommaso D'Odorico;Brandon Bennett

  • Affiliations:
  • School of Computing, University of Leeds, Leeds, United Kingdom;School of Computing, University of Leeds, Leeds, United Kingdom

  • Venue:
  • SC'12 Proceedings of the 2012 international conference on Spatial Cognition VIII
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we formalise an ontology for motion verbs based on classical logic, event calculus, supervaluation and standpoint semantics. We present a theoretical account and a logic-programming implementation of the ontology, which fits within a system aimed at detecting event occurrences in video scenes. Our purpose is to build a bridge between Computer Vision and Knowledge Representation and Reasoning, and to address the issue of concept vagueness in formal ontologies.