Threshold extension of the modified FBLP algorithm

In this paper, two methods are presented for extending the threshold characteristics of the modified forward-backward linear prediction (MFBLP) algorithm due to Tufts and Kumaresan.1 This algorithm estimates angles of arrival of plane waves onto linear arrays of sensors. The first technique proposed, referred to as modified-modified FBLP (M2FBLP), offers 4- to 6-dB threshold extensions over MFBLP for a large number of snapshots, for a particular set of simulation parameters. The second technique, called optimized FBLP (opt-FBLP), offers similar threshold extensions when the number of snapshots is low. The opt-FBLP method is most successful when the number of incident signal components K is 2. The method is therefore viewed as being particularly applicable to the low-angle tracking problem in radar, since it has been shown that there is strong justification to fix the value of K at 2 in this situation. The increase in computational complexity required for M2FBLP over MFBLP is virtually negligible. For opt-FBLP, the increase in computational complexity is minimal for K = 2.