You are here

Low-Shot Detection in Remote Sensing Imagery

Award Information
Agency: Department of Defense
Branch: National Geospatial-Intelligence Agency
Contract: HM047619C0059
Agency Tracking Number: NGA-P2-19-08
Amount: $1,000,000.00
Phase: Phase II
Program: SBIR
Solicitation Topic Code: NGA172-002
Solicitation Number: 17.2
Timeline
Solicitation Year: 2017
Award Year: 2019
Award Start Date (Proposal Award Date): 2019-07-25
Award End Date (Contract End Date): 2021-07-21
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
 Timothy E Fair
 Senior Analyst
 (805) 968-6787
 tfair@toyon.com
Business Contact
 SBIR Coordinator
Phone: (805) 968-6787
Email: sbir@toyon.com
Research Institution
N/A
Abstract

Toyon Research Corporation proposes to develop algorithms that improve the precision and recall of neural networks for low-shot object classification and detection. Our approach is based upon developing a descriptive multi-domain feature representation of the low-shot target as well as the surrounding context. A multi-branch neural network merges the various domains of information to perform accurate classification of low-shot targets. In addition to this approach, samples of low-shot targets will be supplemented with synthetically generated images using traditional computer-aided design.

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

US Flag An Official Website of the United States Government