SBIR-STTR Award

CHATMAN Phase II
Award last edited on: 9/19/2022

Sponsored Program
SBIR
Awarding Agency
DOD : NGA
Total Award Amount
$1,070,487
Award Phase
2
Solicitation Topic Code
OSD221-001
Principal Investigator
Ryan Richards

Company Information

The Stratagem Group Inc

3855 Lewiston Street Suite 250
Aurora, CO 80011
   (484) 994-9271
   N/A
   www.stratagemgroup.com
Location: Single
Congr. District: 06
County: Arapahoe

Phase I

Contract Number: HM047622C0050
Start Date: 7/18/2022    Completed: 4/17/2023
Phase I year
2022
Phase I Amount
$99,941
Reducing the false alarm rate (FAR) of Automated Target Recognition (ATR) algorithms is crucial for intelligence, surveillance, reconnaissance (ISR) and precision target engagement missions. There are many contributing factors that result in higher FAR for deep learning (DL) ATR networks operating on Synthetic Aperture Radar (SAR) imagery, including: image distortions, unrepresentative target signatures, and lack of spatial awareness. Common SAR distortions can both obfuscate target signatures and misrepresent clutter which, for convolutional-based networks especially, has been shown to increase FAR. Further, state-of-the-art (SOTA) ATR networks are not spatially aware, i.e. they cannot exploit information from global or local scene geometries to make more informative predictions. To address these issues and thereby reduce the FAR of ATR algorithms, the Stratagem team will develop CHATMAN: Context-aware Hierarchical graph network for improved ATR performance, a noise-robust Scene Geometry Aided (SGA) ATR framework which distills relations between scene geometries and detected targets to reduce false alarms. CHATMAN is composed of 3 major components: (1) an ATR network, (2) a self-supervised learning (SSL) based semantic analyzer, and (3) a spatial reasoning graph neural network (SRGNN). Our pre-existing ATR SOTA networks will be used to provide class-wise predictions and bounding box coordinates for detected targets in the scene. The semantic analyzer encodes semantics of specific scene geometries for which annotations do not exist (e.g., trees, buildings, road networks) into compressed feature vectors. Finally, the SRGNN corrects ambiguous, or lower confidence, predictions made by the ATR network by learning global and local scene relationships derived from the ATR outputs and semantic feature vectors. For this study, we propose using a privately curated SAR dataset from Capella, a commercial SAR data partner. We propose detecting mixed aircraft (e.g., planes, helicopters, retired air vehicles) with this existing labelled dataset. Our goal is to show that CHATMAN can increase our mean Average Precision (mAP) score with this dataset from 0.84 to greater than 0.90 by reducing false alarms. This effort will deliver a design description document for the SSL and SRGNN networks and quantitative results, including the resultant FAR, the precision-recall curve, and mAP score.

Phase II

Contract Number: HM047623C0036
Start Date: 8/23/2023    Completed: 8/27/2025
Phase II year
2023
Phase II Amount
$970,546
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