Using Features to Reduce LFA and CFLA Clutter - MP 14-13 Navy SBIR FY2013.1 Sol No.: Navy SBIR FY2013.1 Topic No.: N131-050 Topic Title: Using Features to Reduce LFA and CFLA Clutter - MP 14-13 Proposal No.: N131-050-0292 Firm: Metron, Inc. 1818 Library Street Suite 600 Reston, Virginia 20190-6242 Contact: Lawrence Stone Phone: (703) 326-2840 Web Site: www.metsci.com Abstract: Metron has developed a detector-tracker for Mid Frequency Active (MFA). This detector-tracker computes likelihood functions and likelihood ratio surfaces from the un-normalized matched filter output of the MFA system. While doing this we have discovered a number of features that significantly reduce false alarms. The process involves identifying a feature, characterizing its statistical behavior, and developing a likelihood ratio function based on the probability distribution of the feature's response when a target is present to the distribution when no target is present. The power and virtue of working with likelihood ratios is that there is a principled and optimal way to combine this feature information with the likelihood ratio surface produced from the matched filter output, namely multiply the likelihood ratios together to form a cumulative likelihood ratio surface. Peaks in this new surface become candidates for detections. When combined in this fashion, the likelihood ratios from a well-constructed feature will reinforce the peaks due to targets and reduce those due to clutter. This will reduce the false alarm rate without lowering detection probability. We plan to adapt and apply this process to the LFA/CLFA tracker Metron is developing under ONR funding. Benefits: The goal of the work proposed for this SBIR is two-fold. The first is to identify promising features and adapt them for LFA/CLFA to produce a reduction in clutter. This includes developing a methodology for including features into the LFA/CLFA detector-tracker. This methodology will provide a template for developing and including new features in a principled and effective way, namely develop a likelihood ratio function for the feature and then multiply it into the existing likelihood ratio surface. This is a modular process which does not require redesign of the detector-tracker code base. The second is to examine detection thresholds that are a function of beam and Doppler to reduce clutter contacts that fall off the Doppler ridge. Increasing the threshold in those regions will help to reduce clutter detections Return