You are here

Template Generation From A Small Number of Views

Award Information
Agency: Department of Defense
Branch: Army
Contract: DAAB07-02-C-G202
Agency Tracking Number: A012-1688
Amount: $69,992.00
Phase: Phase I
Program: SBIR
Solicitation Topic Code: N/A
Solicitation Number: N/A
Timeline
Solicitation Year: N/A
Award Year: 2002
Award Start Date (Proposal Award Date): N/A
Award End Date (Contract End Date): N/A
Small Business Information
10190 Bannock Street, Suite 246
Northglenn, CO 80260
United States
DUNS: 787644921
HUBZone Owned: No
Woman Owned: No
Socially and Economically Disadvantaged: No
Principal Investigator
 W. Kober
 President
 (720) 872-2145
 wkober@datafusion.com
Business Contact
 W. Kober
Title: President
Phone: (720) 872-2145
Email: wkober@datafusion.com
Research Institution
N/A
Abstract

"Data Fusion Corporation (DFC), along with Lockheed Martin Missiles and Space Co. (LMSC), propose the development of a system for synthesizing alternate viewpoint images of an object which has been previously sensed via a short series of images. Thissystem will be used to support model-based object recognition and cataloguing of unknown objects.DFC's approach will be to: enhance LMSC's previously developed system for feature-based matching in image sequences via the incorporation of anisotropic diffusion and morphological operators, and extend DFC's and LMSC's previously developed point-transfervia geometric invariants software for producing novel views using trinocular invariants. DFC's long-term goal is to produce a real-time version of this system. A real-time version is one that produces 3-D models as the images come in (with processingdelays of a fraction of a second). This will require a high level of automation and powerful processing resources. Potential benefactors are in the domains of virtual reality, robotics, industrial inspection, autonomous vehicles, militaryreconnaissance, etc."

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

US Flag An Official Website of the United States Government