You are here

Sensor Modality Translation through Contrastive Deep Learning

Award Information
Agency: Department of Defense
Branch: Navy
Contract: N68335-23-C-0612
Agency Tracking Number: N23A-T013-0090
Amount: $139,846.00
Phase: Phase I
Program: STTR
Solicitation Topic Code: N23A-T013
Solicitation Number: 23.A
Timeline
Solicitation Year: 2023
Award Year: 2023
Award Start Date (Proposal Award Date): 2023-08-03
Award End Date (Contract End Date): 2024-01-30
Small Business Information
20 New England Business Center
Andover, MA 01810-1111
United States
DUNS: 073800062
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 Christian Smith
 (978) 738-8269
 cwsmith@psicorp.com
Business Contact
 William Marinelli
Phone: (978) 738-8226
Email: marinelli@psicorp.com
Research Institution
 The University of Rhode Island
 Theodore Myatt
 
70 Lower College Road
Kingston, RI 02881
United States

 (401) 874-4328
 Nonprofit College or University
Abstract

Physical Sciences Inc. (PSI), in collaboration with the University of Rhode Island, proposes to develop an advanced algorithm suite for data translation across sensing modalities to support the development of automated target recognition and classification algorithms for Unmanned Underwater Vehicles. The proposed Deep Diffusion Sensor Translation (DDST) leverages recent advancements in generative artificial intelligence, and latent diffusion models in particular, to enable highly realistic data synthesis to supplement these underwater ATR datasets. The DDST tool will be capable of translating between sidescan sonar, forward looking sonar, synthetic aperture sonar, imaging magnetometry, and visible sensing modalities. The DDST incorporates advancements in underwater image enhancement and three-dimensional scene reconstruction to normalize variability across instruments, environments, and sensing conditions. The DDST will also leverage PSI’s computer vision and image fusion expertise developed under multiple DoD programs, through customization of an in-house super-resolution technique to the task of enhancing DDST inputs and outputs. The DDST technology will produce synthetic sensor outputs with quantifiable accuracy, achieving acoustical and optical reflectivity accuracies with PSNRs of 30dB and 25dB respectively.

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

US Flag An Official Website of the United States Government