TARGET RECOGNITION USING SPECTRAL/SPATIAL TECHNIQUES

Award Information
Agency:
Department of Defense
Branch
Air Force
Amount:
$496,968.00
Award Year:
1993
Program:
SBIR
Phase:
Phase II
Contract:
n/a
Award Id:
14848
Agency Tracking Number:
14848
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
45 Manning Road, Billerica, MA, 01821
Hubzone Owned:
N
Minority Owned:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
Frank J Iannarilli Jr
Principal Investigator
(508) 663-9500
Business Contact:
() -
Research Institute:
n/a
Abstract
THE EMERGENCE OF EO MULTISPECTRAL IMAGING TECHNOLGOY MOTIVATES EXLORATION OF POTENTIAL IMPROVEMENTS IN AUTOMATIC TARGET RECOGNITION (ATR) SYSTEM PERFORMANCE USING NOVEL SPECTRAL/SPATIAL TECHNIQUES. SUCHCONCEPTS OFFER A PROMISING COMBINATION OF COMPLEMENTARY TECHNIQUES, WITH THE SPECTRAL COMPONENET REDUCING CLUTTER AMBIGUITY FOR SPATIAL PROCESSING WHICH SIFTS HIGH-VALUE TARGETS FROM THOSE OF NON-INTEREST, E.G., TANK FROM TRUCK. THE SPECTRAL/SPATIAL ALGORITHM CONCEPTS PROPOSED BY AERODYNE INTEGRATE AND EXPLOIT MODEL-PREDICTED KNOWLEDGE USING MARKOV RANDOM FIELDS TO REPRESENT SPATIAL DEPENDENCIES OF PRODICTED TARGET SPECTRAL ATTRIBUTES. OUR CONCEIVED MODEL-BASED SPECTRAL DISCRIMINATION PROCESS, RESISTANT TO TARGET OCCLUSIONS (E.G., CAMOUFLAGE), PRODUCES APRE-CLASSIFIED SCENE. AMBIGUITIES WITH IN THIS PROCESSED SCENE ARE SIGNIFICANTLY REDUCED UTILIZING A DYNAMIC PROCESS WHICH EXPLOITS JOINTSPECTRAL AND SPATIAL CONTEXTUAL INFORMATION, RESTORING WEAK AND TOTALLY OCCLUDED TARGET PIXELS. FINALLY POSE AND SCALE-INVARIANT RECOGNITION IS ACHIEVED USING A MODEL-BASED CONTENT-ADDRESSABLE MEMORY. THE RESULTING ALOGRITHMIC STRUCTURE IS INHERENTLY PARALLEL, PROMISING COMPUTATIONAL FEASIBILITY VIA IMPLEMENTATION ON MASSIVLEY PARALLEL NEURAL NETWORKS. THE PHASE I INVESTIGATION WILL ASSESS THE EXTENT OF EXPLOITABLE SPECTRAL DIFFERENCES BETWEEN TARGETS OF INTEREST AND CLUTTER. A SURVEY OF EMERGING MULTISPECTRAL IMAGING CAPABILITY WILL BE COUPLED WITH FOCUSED ANALYSIS AND TESTING OF KEY DETAILS OF THE CONCEPT ALGORITHMS TO DETERMINE THE FEASIBILITY OF PHASE II ALOGRITHM IMPLEMENTATION.

* information listed above is at the time of submission.

Agency Micro-sites


SBA logo

Department of Agriculture logo

Department of Commerce logo

Department of Defense logo

Department of Education logo

Department of Energy logo

Department of Health and Human Services logo

Department of Homeland Security logo

Department of Transportation logo

Enviromental Protection Agency logo

National Aeronautics and Space Administration logo

National Science Foundation logo
US Flag An Official Website of the United States Government