Multisource Data Registration Tools
SBIR FY04.1 Topic AF04-226
Department of Defense (DOD)/Air Force - Sensors Directorate

The entire solicitation may be viewed at http://www.acq.osd.mil/sadbu/sbir/solicitations/sbir041/index.htm

AF04-226 TITLE: Multisource Data Registration Tools

TECHNOLOGY AREAS: Sensors, Electronics, Battlespace

ACQUISITION PROGRAM: AWACS RSIP (E-3)

OBJECTIVE: Data registration from multiple sources must take place in real time to support required capabilities ranging from rapid detection and engagement of mobile targets to "first look, first shot, first kill" against airborne threats.

DESCRIPTION: The objective of this effort is to develop autonomous registration technology in the form of a software toolkit for the spatial alignment of image, signals intelligence (SIGINT), and ground moving target indicator (GMTI) data collected from the battlespace. The focus of this research is to develop the novel approaches to georegistration by first, developing geo-reference invariant features that can be extracted from each data source and second, developing algorithms for correlating/integrating these features across the multiple data sources and a fiducial database for relative and absolute registration. Examples of features that cross multiple source data domains could be radio/TV transmission towers, command and control centers, road intersections, fixed search radar towers, and cellular phone towers. Correlation/integration algorithms will tie disparate types of sensor data together with the fiducial database while exploiting the knowledge of physics and phenomenological models (exact or approximate) of sensors and source types that might be available. The research will exploit innovative approaches including multi-agent knowledge-based systems, neural networks, modeling field theory, multiresolutional architectures, evolutionary computation. Most appropriate approaches will be identified for each sensor, source type, and for integrating/correlating all the data and available knowledge. The result will be a reliable, flexible system that can coregister multiple sensor data, estimate and account for errors and uncertainties, and identify measures of effectiveness for automatic convergence to minimize human intervention. The algorithms will be implemented as a software toolkit to enable the flexible system integration. The effort should take advantage of innovative approaches to integrated intelligent computational systems exploiting the current knowledge about the integrative abilities of human mind.

PHASE I: Investigate innovative approaches to the development of geo-reference invariant features and correlation/integration algorithms. Develop and demonstrate a proof of concept for multisource data registration using salient features on a limited multisource data set that would be provided by the Government. Develop a software design that can be extended to integrate different algorithmic approaches based on a generic concept of a feature.

PHASE II: Further diversify and enhance the prototype developed in Phase I effort to support additional functionality, knowledge, information, sensors, and sources. Develop and integrate a complete suite of data registration algorithms in the form of a software toolkit. Characterize performance over a wide range of data including multisource imagery, GMTI, and SIGINT. Identify transition pathways to the warfighter.

DUAL USE COMMERCIALIZATION: This technology is directly applicable to a broad range of military applications. Potential commercial application areas include remote sensing, oil exploration, security systems, and extensions of this technology to integrating data beyond geo-registration domain to medical diagnostics, biophysical and drug-discovery applications, financial industry, internet search engines, application-specific information search engines, and other commercial applications.

REFERENCES: 1. Perlovsky, L.I. (2001). Neural Networks and Intellect: using model-based concepts. Oxford University Press, New York, NY.

2. Meystel, A.M., Albus, J.S. (2001). Intelligent Systems: Architecture, Design, Control.
Wiley-Interscience, New York, NY.

3. Hall, D.L. & Llinas, J. (Editors),1997, Handbook of Multisensor Data Fusion, CRC Press.

KEYWORDS: georegistration, correlation, integration, multiple sensors, intelligent systems, image registration,

Questions about SBIR and Solicitation Topics

TECHNICAL POINT OF CONTACT:

Dr. Leonid Perlovsky
Phone:
Fax:
Email:

SENSORS DIRECTORATE PROGRAM MANAGER:

Marleen Fannin
, x4117

Between October 1 and November 28, 2003, you may talk directly with the Topic Authors to ask technical questions about the topics. Their names, phone numbers, and e-mail addresses are listed within each solicitation topic above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting December 1, when DoD begins accepting proposals for this solicitation. However, proposers may still submit written questions about solicitation topics through the SBIR/STTR Interactive Topic Information System (SITIS), in which the questioner and respondent remain anonymous and all questions and answers are posted electronically for general viewing until the solicitation closes. All proposers are advised to monitor SITIS (04.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 04.1 topic under which they are proposing.