CHATMAN Phase II

Reducing the False Alarm Rate (FAR) of Automated Target Recognition (ATR) algorithms for Synthetic Aperture Radar (SAR) imagery is crucial for Intelligence, Surveillance, Reconnaissance (ISR) and precision target engagement missions. While modern Deep Learning (DL) ATR networks have demonstrated advanced predictive capabilities and generalization for SAR imagery, they lack spatial awareness, resulting in a higher FAR. ATR networks are not functionally equipped to learn semantic separability of scene geometries external to the target ontology, hindering their ability to distill contextual relevancy between objects to both increase precision and reduce FAR. To address these network deficiencies, the Stratagem team proposed a solution to the Phase I NGA OSD221-001 SBIR called: Context-aware Hierarchical graph network for improved ATR performance (CHATMAN), a Scene Geometry Aided (SGA) ATR framework which distills relations between external scene geometries and detected targets to reduce false alarms. During Phase II, the Stratagem team will address these improvement opportunities, mature detection capabilities, and transition into an operational codebase. Specifically, we seek to: 1. Enhance the Phase I architecture to further improve detection results; 2. Extend detection capabilities via multimodal data fusion; and 3. Create the foundational infrastructure and utilities for deployment to an NGA cloud-hosted environment