You are here

Blending Classical Model-Based Target Classification and Identification Approaches with Data-Driven Artificial Intelligence

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N68335-19-C-0109
Agency Tracking Number: N18B-033-0032
Amount: $124,999.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: N18B-T033
Solicitation Number: 18.B
Timeline
Solicitation Year: 2018
Award Year: 2019
Award Start Date (Proposal Award Date): 2018-10-15
Award End Date (Contract End Date): 2019-04-25
Small Business Information
6800 Cortona Drive
Goleta, CA 93117
United States
DUNS: 054672662
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Abhejit Rajagopal Abhejit Rajagopal
 Analyst
 (805) 968-6787
 arajagopal@toyon.com
Business Contact
 SBIR Coordinator
Phone: (805) 968-6787
Email: sbir@toyon.com
Research Institution
 University of California, Santa Barbara
 Kevin Stewart Kevin Stewart
 
3227 Cheadle Hall
Santa Barbara, CA 93106
United States

 (805) 893-5197
 Nonprofit college or university
Abstract

Toyon Research Corp. and the University of California propose to develop innovative algorithms to perform automatic target recognition (ATR), localization, and classification of maritime and land targets in EO/IR, LiDAR, and SAR imagery. The proposed algorithms are based on recent developments made at the University of California, which outline a strong mathematical framework for naturally blending classical model-based target recognition algorithms with modern data-driven machine-learning approaches, such as those utilizing deep learning. Specifically, this proposal presents a mathematical formalism for incorporating heuristics and feature-based detection algorithms directly into a deep neural networks (DNNs), which can be further trained and optimized for a particular ATR task specified by example or model-data. The resulting system provides a mechanism for Navy operators and DoD algorithm designers to leverage existing model-based ATR algorithms, with a known threshold of baseline-performance, to systematically design deeper and more-robust neural-network-based algorithms that can be naturally optimized and augmented using modern machine-learning approaches. Furthermore, while the proposed algorithmic framework is largely agnostic to the particular imaging-modality, we demonstrate how it can be specifically tuned to discover features that are unique to particular modalities, in either the spatial or the spatial-frequency domain, mitigating uncertainties that arise in various environmental or

* Information listed above is at the time of submission. *

US Flag An Official Website of the United States Government