A multi-sensor inference and data fusion method for tracking small, manoeuvrable maritime craft in cluttered regions
Barr, Jordi, Uney, Murat; id_orcid 0000-0001-6561-0406, Clark, Daniel, Miller, Dave, Porter, Matthew, Gning, Amadou, Julier, Simon · Edinburgh Research Explorer (University of Edinburgh) · 2013
We present an inference and data fusion method for tracking maritime Fast Inshore Attack Craft (FIACs) using multiple sensors. The scenario addressed encompasses littoral, counter-piracy and maritime constabulary operations. The problem space is characterised by mixed sensor modalities, non-stationary and spatially-varying non-Gaussian clutter, intermittent observations and a high false alarm rate. Our method combines the Probability Hypothesis Density (PHD) Filter for multi-target Bayesian inference with Generalised Co-variance Intersection (GCI) for decentralised data fusion. We outline the development and testing of our solution using Electro-Optic and radar observations of marine traffic in the Solent. These data are complemented by ground truth positional data of marine traffic including high-frequency positional estimates of two representative FIACs. Our system has been deployed both online and in real time. We carry out a number of experiments designed to show the efficacy of the algorithms in representative scenarios. The performance of our algorithms is quantified using multi-target inference metrics. We show that the combination of PHD and GCI has many advantages over traditional inference and fusion methods, particularly in cluttered environments.