Fusion of Elliptical Extended Object Estimates Parameterized With Orientation and Axes Lengths

This article considers the tracking of elliptical extended targets parameterized by center, orientation, and semiaxes. The focus this lies on fusion target estimates, e.g., from multiple sensors, handling ambiguities in parameterization unclear meaning mean square error. For purpose, we introduce a novel Bayesian framework for elliptic extent estimation based two new concepts: 1) A probability density function ellipses called random ellipse which incorporates that come with parameterization, 2) minimum Gaussian Wasserstein (MMGW) estimate, is optimal respect to squared (GW) distance-A suitable distance metric ellipses. We develop practical algorithms approximating MMGW estimate. Different implementations, Monte Carlo simulation, are introduced compared state-of-the-art methods, highlighting benefits estimators tailored GW distance.