Target association using detection methods

This paper presents a residual-based scheme for solving the radar track association problem using bearings-only measurements. To accomplish track association between two stations, we analyze the residuals of a bank of nonlinear filters called modified gain extended Kalman filters (MGKEFs). Once the tracks have been associated between two stations, tracks from additional stations may be associated with tracks from the first two stations by checking algebraic parity equations. Traditional track association methods rely on the local stations´ estimated target positions and error variances, which may be quite inaccurate when using bearings-only measurements. Our methods bypass this difficulty, since our filters use raw data from two stations. An example illustrates the effectiveness of our methods.