Optical Correlator for Realtime Pattern Recognition Applications
Navy SBIR 2010.3 - Topic N103-206
NAVAIR - Mrs. Janet McGovern - [email protected]
Opens: August 17, 2010 - Closes: September 15, 2010

N103-206 TITLE: Optical Correlator for Realtime Pattern Recognition Applications

TECHNOLOGY AREAS: Information Systems, Sensors, Weapons

ACQUISITION PROGRAM: PMA-281, Cruise Missile Command & Control; Joint Mission Planning System

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 optical correlator to filter sensor data streams searching for and automatically recognizing, classifying and potentially identifying, multiple battlefield targets.

DESCRIPTION: Current Automatic Target Recognition (ATR) technology can only provide a limited number of template matches per second because they are constrained by the processing speeds of the digital electronic processors. Optical systems can operate at much higher speeds thus providing a manifold orders-of-magnitude increase over current electronic systems. As an Unmanned Aerial System (UAS) approaches a target, there is no way to predict exactly how that target will look so multiple images must be provided for comparison. Even more difficult, if the aircraft is seeking targets in general (i.e. tanks, missile launchers, warships, jeeps, etc.) rather than a specific target, the number of templates required to match the target is much larger.

Under current technology conditions, a UAS sensor or sensor integrated into a missile system might present up to 60 image frames per second to the analyzer to be screened. If a digital image analyzer can process 60 frames per second, this is less than two templates per image. To provide sufficient analytical speed, optical processors are probably the only viable method. An optical correlator operating at over several thousand frames per second potentially could check each image against a large set of target templates in a second. Furthermore, any data that can be rendered as optical images can be addressed this way. Radar images are an easy example. Other sorts of data, such as frequency and location of electronic data transfers that preceded previous terrorist attacks could be compared to current electronic data traffic. Any data which can be arranged into predictable 2-dimensional patterns would be applicable for this.

PHASE I: Develop and demonstrate an initial conceptual design for an optical correlator sized for integration and operation in weapon systems that will be able to check each frame in a video feed against thousands of target templates.

PHASE II: Based on Phase I results, design and develop a prototype optical correlator and demonstrate that several thousand target templates can be tested against each video frame in a normal speed video input. Show successful classification and identification of multiple target types in an operational environment.

PHASE III: Transition optical correlator into applicable Navy electronic warfare assets and commercial applications such as manufacturing, homeland security, and medical pattern recognition applications.

PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Optical Correlators will be useful in any application that would benefit from rapid real time identification of targets/patterns in images. This could vary from medical images, to security work - facial recognition, fingerprint classification, identifying weapons in scanned luggage, and home-land security. It could be used for automated searches of graphical data on the internet. Once the leap is made to any data that can be put into a two-dimensional array, data such as crop health vs. date could be used to better predict agricultural outcomes.

REFERENCES:
1. Birch, Phillip, Young, Rupert, & Chatwin, Chris. (2009), "Volume holograms for optical correlation". SPIE Newsroom. http://spie.org/x33635.xml?ArticleID=x33635

2. Chao, Tien-Hsin, Zhou, Hanying, & Reyes, George. "High-speed Optical Object Recognition Processor With Massive Holographic Memory". http://trs-new.jpl.nasa.gov/dspace/bitstream/2014/10073/1/02-2185.pdf

3. Zhang,Yanxin & Li, Sumei. (2003)."Existence problem of optical correlation based pattern recognition" Science in China Series G: Physics Mechanics and Astronomy, 46(6), 1672-1799. Science in China Press, co-published with Springer-Verlag GmbH.

KEYWORDS: Sensors; Information; Optical Processing; Pattern Recognition; Automatic Target Recognition; Optical Correlator

** TOPIC AUTHOR (TPOC) **
DoD Notice:  
Between July 20 and August 16, 2010, you may talk directly with the Topic Authors 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 August 17, 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 (10.3 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 10.3 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.