Tracking of Multiple Maneuvering Random Hypersurface Extended Objects Using High Resolution Sensors

With the increased resolution capability of modern sensors, an object should be considered as extended if target extent is larger than sensor resolution. Multiple maneuvering tracking (MMEOT) uses not only measurements centroid but also high-resolution which may resolve individual features or measurement sources. MMEOT aims to jointly estimate number, states, and extension states. However, unknown time-varying maneuvers multiple objects produce difficulties in terms accurate estimation. For star-convex using random hypersurface models (RHMs) particular, their complex behaviors are difficult described accurately handled effectively. To deal with these problems, this paper proposes interacting model Gaussian mixture probability hypothesis density (IMM-GMPHD) filter for tracking. In filter, linear maneuver derived from RHMs utilized describe different turn accurately. Based on these, IMM-GMPHD filtering recursive form given by deriving new update merging formulas probabilities objects. components posterior intensities pruned merged More importantly, geometrical significance states fully exploited filter. This contributes estimation extensions. Simulation results demonstrate effectiveness proposed approach—it can obtain joint kinematic extensions scenarios.