A Bayesian approach to extended object tracking and tracking of loosely structured target groups

Abstract

In algorithms for tracking and sensor data fusion the targets to be tracked are usually considered as point source objects; i.e., compared to the sensor resolution their extension is neglected. Due to the increasing resolution capabilities of modern sensors, however, this assumption is often not valid: different scattering centers of an object can cause distinct detections when passing the signal processing chain. Examples of extended targets are found in short-range applications (littoral surveillance, autonomous weapons, or robotics). As an extended target also a collectively moving, loosely structured group can be considered. This point of view is all the more appropriate, the smaller the mutual distances between the individual targets are due to the resulting data association and resolution conflicts any attempt of tracking the individual objects is no longer reasonable. With simulated sensor data produced by a partly resolvable aircraft formation the addressed phenomena are illustrated and a Bayesian solution to the resulting tracking problem is proposed. Ellipsoidal object extensions are modeled by random matrices and treated as additional state variables to be estimated or 'tracked'. We expect that the resulting tracking algorithms are relevant also for tracking large, collectively moving target swarms.