Innovative Algorithms for the Categorization of Mine-Like Objects Using Standard Sonar Return Data.

Detection and prosecution of naval surface and underwater mines is an increasingly important problem facing naval forces across the globe. Despite the need for strong mine countermeasure (MCM) technologies and capabilities, resources devoted to MCM have been limited in general, and are likely to remain sparse. There is therefore an urgent need to extract more actionable intelligence from the data streams of existing systems. Active sonar is the leading marine mine-hunting technology. The work proposed here aims to extend the capabilities of existing MCM systems using a combination of multi-ping processing and feature based classification to improve weak target detection and reduce the false contact rate. These algorithms will increase search rate and reduce operator review time for existing systems without the need for costly hardware upgrades. The algorithms will be capable of real-time processing on the existing PMA resources. By further exploiting existing sonar data streams this work will increase the increase the effectiveness of these critical Navy assets.