ASSOCIATION OF TRACKS FROM OVER THE HORIZON RADAR

In Over-The-Horizon Radar (OTHR), multiple ionospheric layers cause se veral tracks per target to be observed. This effect causes ambiguities in target identification and track coordinate registration. A pattern classification approach is proposed for associating tracks. Neural ne tworks and statistical methods are applied to combine track affinities and associate pairs of tracks. The proposed approach provides a pract ical and efficient way of dealing with multiple track association when the number of targets is large and optimal. Bayesian hypothesis testi ng is not practical.