Traditional deep learning (DL) classifiers often ignore contextual data, limiting complex threat scenario analysis. A new approach, incorporating a wide range of contextual data, is needed to improve object of interest classification, tracking, and targeting. Clostraâs CT-ID (Contextual Threat Identification) will incorporate multi-sensor, time-series, and high-level contextual data, improving threat classification accuracy and allowing salvo firing control to confidently target high-priority objects. Approved for Public Release | 21-MDA-11013 (19 Nov 21
