STATISTICAL PERFORMANCE ANALYSIS OF TRACK INITIATION TECHNIQUES

This paper analyzes the statistical performance of track initiation me thods, It evaluates, by considering a track initiation as a problem of signal detection, the track detection probabilities and false track p robabilities of four popular approaches: the rule-based method, the lo gic-based method, the Hough transform, and the modified Hough transfor m techniques, The first two methods detect the existence of tracks in a sequential fashion, and the last two are image processing techniques that initiate tracks using a batch of frames, The analytical expressi ons for the track detection probability and false track probability of the four methods are derived to predict their capabilities in capturi ng new tracks: and in rejecting false tracks due to false alarms and c lutter background, Monte Carlo simulations are performed to confirm th e analysis, It is observed that when the false track probability is he ld fixed, the logic-based and the modified Hough transform techniques have good detection performances.