Track-to-Track Association Using Attributes
Yaakov Bar‐Shalom, Huimin Chen · 2007
The problem of track-to-track association–a prerequisite for the fusion of tracks–has been considered in the literature for tracks described by kinematic states and, more recently, has been general-ized to include additional (continuous valued) feature and (discrete valued) attribute variables which pertain to those tracks. These approaches allow the search for the maximum likelihood (ML) or maximum a posteriori (MAP) association. However, while for kine-matic variables there is a “gating ” procedure based on a Gaus-sian distribution–which corresponds to a Neyman-Pearson test of “common origin ” (actually, “same kinematic state”) with selectable power–there is no simple counterpart of this for attributes. The sufficient statistic for the optimal association test (in the Neyman-Pearson sense) based on discrete-valued target classification infor-mation observables (attributes) is derived and its relationship with the class probability vector is discussed. Based on this, “attribute gates ” are presented, which allow a Neyman-Pearson test for “same class ” with the desired power.