Airborne Behaviour Monitoring Using Regular-Expressions Based Pattern Matching

This paper addresses the problem of target manoeuvre detection and behaviour recognition using string-matching techniques which could bring a great impact to the multiple UAV operations. The overall proposed solution consists of a trajectory analysis tool, which classifies the target position in time into a sequence of driving modes, and a string-matching method. For the latter, two techniques are described and compared: a classical approach based on simple strings and a newly proposed regular-expressions-based method. The advantages obtained from the use of regular expressions are extensively analysed, and results from numerical simulations supporting our conclusions are provided.