Novel ATR Algorithms for FLIR and SAR Sensor Fusion

Award Information
Agency:
Department of Defense
Branch
Army
Amount:
$100,000.00
Award Year:
1997
Program:
SBIR
Phase:
Phase I
Contract:
n/a
Award Id:
37067
Agency Tracking Number:
37067
Solicitation Year:
n/a
Solicitation Topic Code:
n/a
Solicitation Number:
n/a
Small Business Information
500 West Cummings Park, Suite 3000, Woburn, MA, 01801
Hubzone Owned:
N
Minority Owned:
N
Woman Owned:
N
Duns:
n/a
Principal Investigator:
Raman K. Mehra
(617) 933-5355
Business Contact:
() -
Research Institute:
n/a
Abstract
Automated surveillance techniques for target detection, classification, and identification are critically dependent on information processing based on mnltisensor integration. The full utilization of these various sensor modes requires the development of enhanced information processing algorithms. This proposal describes a novel algorithm for automatic target recognition (ATR) using both FLIR and SAR sensor fusion. This algorithm is built around three modules: preprocessing, registration, and model based fusion and classification. The technologies for this novel ATR algorithm are based on a number of pioneering state-of-the-art algorithms for automated target detection, recognition, and fusion developed at Scientific Systems Company (SSC) and Nichols Research Corporation (NRC). Specific Phase I tasks are: 1) Acquire FLIR and SAR data for algo rithm training and testing 2) Develop the Novel ATR Algorithm for FLIR and SAR sensor fusion. This task will involve three subtasks. 2.1) Develop the Preprocessing Module. 2.2) Develop the Registration Module. 2.3) Develop the Classification Module. 3) Test and evaluate novel ATR algorithm on real/synthetic FLIR and SAR data. 4) Final report and Phase II recommendations. Phase II will extend this work to fuse information from multiple data sets (MT'T, SAR, and FLIR radar) as well as from multiple data sensors (radar, acoustic, and electro-optic sensors). NRC will provide support in the area of neural network classification. Dr. Chellappa from the University of Maryland will provide support in the areas of ATR and sensor registration. Northrop Grumman Norden Systems will provide support in the SAR area. Automatic Target Detection and Recognition (ATD/R) is one of the key technologies for global surveillance, precision strike, air superiority and defense which are three of the seven science and technology thrust areas identified by the Director of Defense Research and Engineering. Commercial applications of advanced ATD/R systems exist in several areas such as: radar, biometric identification, industrial inspection, medical screening and diagnosis, failure detection and identification, and remote sensing.

* 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