TECHNOLOGY AREAS: Information Systems, Ground/Sea Vehicles, Sensors, Battlespace

ACQUISITION PROGRAM: PMS 435 Photonics Mast ACATIII & Integrated Submarine Imaging System ACATIV

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), which controls the export and import of defense-related material and services. Offerors must disclose any proposed use of foreign nationals, their country of origin, and what tasks each would accomplish in the statement of work in accordance with section 3.5.b.(7) of the solicitation.

OBJECTIVE: Develop an algorithm(s) capable of automatically classifying and recognizing marine targets in imagery from submarine imaging systems. The algorithm(s) will also be able to extract target parameters such as length, height, overall configuration (e.g., superstructure, stack, mast locations) from the imagery. This information will be fed to a marine target database to determine the target�s identification.

DESCRIPTION: Enhanced situational awareness is driving many new capabilities (e.g. Automatic Range Finding (ARF)). Littoral operations frequently involve a large number of marine targets (fishing fleets, e.g.) that may be intermingled with potentially hostile targets. Imaging systems offer the potential for rapid and accurate target detection and classification. In addition, the large number of contacts may cause operator overload. Automatic target detection and classification can reduce operator workload, allow for less skilled operators and improve classification and detection thresholds. Automatic Target Recognition (ATR) includes the ability to distinguish potentially hostile targets from similarly sized non-hostile targets. For example, the algorithm should be able to distinguish between a cruiser and a Coast Guard cutter.

This topic seeks to identify innovative approaches to ATR in difficult operating conditions including choppy seas, low visibility, water droplets on the head window, and a variety of weather conditions. The algorithm(s) should be able to operate on data from detection and tracking algorithms including bearing, bearing rate, size, and on imagery from the full spectrum of imaging sensors including visible color and black & white, LWIR, SWIR, and MWIR sensors in multiple formats including SDTV and HDTV. As a goal, it should extract relevant parameters from each target in less than 1 second. ATR capability should not require an operator trained in recognizing the huge variety of marine targets and should provide enough information to a marine target database to facilitate identification. The preferred implementation of this algorithm(s) is in the form of a software program capable of being run on COTS general purpose processors.

PHASE I: Research, evaluate and select Automatic Target Recognition algorithms. Perform design and analysis of Automatic Target Recognition algorithms, define their performance characteristics (including, but not limited to parameters extracted, processor requirements, processing speed and outputs).

PHASE II: Develop an implementation of the ATR algorithm(s) that will operate on stand alone COTS hardware, ready for a land based demonstration using actual unclassified periscope data. Document the design and test results in a final report.

PHASE III: If successfully demonstrated in Phase II, participate in a submarine image processing system subsystem laboratory integration and at sea testing. Fleet implementation may be accomplished through Technology Insertion (TI) upgrade to existing submarine imaging systems.

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Harbor surveillance for homeland security, law enforcement surveillance, and industrial security are possible commercial applications of such software.

REFERENCES:
1. Automatic Object Recognition: Proceedings, Hatem Nasr, Editor, Society of Photo Optical (1991)

2. Javidi, Bahram; Smart imaging systems, SPIE (2001)

3. Javidi, Bahram; Image Recognition and Classification, CRC (2002)

4. Javidi, Bahram;Optical Information Processing, Proceedings of SPIE (various)

5. The Infrared and Electro-Optical Handbook, Frederick G. Smith, Editor.

KEYWORDS: Automatic Target Classification; Automatic Target Recognition; Electro-Optics; Periscopes; Image Processing; Classification

TPOC: Ken Pietrzak
Phone: (401)832-7847
Fax: (401)832-7336
Email: [email protected]
2nd TPOC: Carl Lindstrom
Phone: (401)832-5531
Fax: (401)832-7336
Email: [email protected]

** TOPIC AUTHOR (TPOC) **

DoD Notice:   Between November 13 and December 9, 2007, you may talk directly with the Topic Author(s) to ask technical questions about the topics. Their contact information is listed above. For reasons of competitive fairness, direct communication between proposers and topic authors is not allowed starting December 10, 2007, when DoD begins accepting proposals for this solicitation.

However, proposers may still submit written questions about solicitation topics through the DoD's 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 (08.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 08.1 topic under which they are proposing.

If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk at (866) 724-7457 or email weblink.