From Numerical to Symbolic Data during the Recognition of Scenarii

  • Authors:
  • S. Loriette-Rougegrez

  • Affiliations:
  • -

  • Venue:
  • AISC '02/Calculemus '02 Proceedings of the Joint International Conferences on Artificial Intelligence, Automated Reasoning, and Symbolic Computation
  • Year:
  • 2002

Quantified Score

Hi-index 0.00

Visualization

Abstract

The objective of this paper is to present a system that is able to recognize the occurrence of a scenario evolving over time and space. Scenarii are considered to be made up of several stages. The transition from a stage to another one requires the satisfaction of conditions. These features have led us to the construction of a graph which is run by means of a rule-based system. Transitions are validated with the transformation of numerical data into symbolic ones. Data's uncertainty is considered by means of the computation of an evidence's mass for each transition. The system described in this paper is applied to the recognition of maneuvers performed by a car driver.