Persistent Maritime Target Tracking Using Automated Target Fingerprinting and Discrimination

The ability to explore, analyze, and find hostile actions/intent behavior within this data is a complex task and requires learning of motion sequence temporal patterns from long term tracks of multiple vessels of interest. There is, therefore, a major need to develop robust, efficient, and reliable identification and tracking techniques to identify selected targets, and to maintain tracks for selected critical targets that undergo long periods of coverage loss and/or are immersed in target dense environments. Traditionally, tracking and identification have been considered separately; we identify a target first, and then we track it kinematically to sustain the identification. The difficulty with separate identification and tracking is that neither task is sufficient by itself to satisfy the demands of the other. We need to incorporate the distinctive target signature information into the tracker, so that identification and tracking, or fingerprinting and tracking, perform together as a unit. The proposed work extends ongoing RDRTec/Leidos maritime classification aids (MCA) and feature-aided tracking development activities that utilize high range resolution (HRR) and inverse synthetic aperture radar (ISAR) to dramatically improve track identity lifetime (TIL) through highly dense target environment as well as through extended overage gap time.