N161-018 TITLE: Physics-Based Maritime Target Classification and False Alarms Mitigation

TECHNOLOGY AREA(S): Air Platform, Sensors

ACQUISITION PROGRAM: PMA 299 Program Office

The technology within this topic is restricted under the International Traffic in Arms Regulation (ITAR), 22 CFR Parts 120-130, which controls the export and import of defense-related material and services, including export of sensitive technical data, or the Export Administration Regulation (EAR), 15 CFR Parts 730-774, which controls dual use items. Offerors must disclose any proposed use of foreign nationals (FNs), their country(ies) of origin, the type of visa or work permit possessed, and the statement of work (SOW) tasks intended for accomplishment by the FN(s) in accordance with section 5.4.c.(8) of the solicitation. Offerors are advised foreign nationals proposed to perform on this topic may be restricted due to the technical data under US Export Control Laws.

OBJECTIVE: Develop near real-time computationally efficient machine learning techniques to significantly improve classification performance of Inverse Synthetic Aperture Radar (ISAR) imagery Synthetic Aperture Radar (SAR) imagery and High Range Resolution (HRR) based maritime classification aids in the presence of vessels not resident in an existing classification database from returns.

DESCRIPTION: Improved maritime situational awareness is an ongoing Navy operational need. Current state of the art maritime classification aids using ISAR, SAR and HRR returns rely on extensive databases containing individual vessel dimensional information (i.e., length overall, superstructure(s) location and dimensions, mast(s) positions). When presented with vessels not in the database inability to classify or improper classification may result. In some instances the particular fine-class of vessel may be resident in the database but subtle variations of the topside configuration generate classification challenges. Here we seek to leverage the complex-valued radar returns from a limited number of viewing angles and knowledge of scattering physics of canonical shapes (e.g., point scatters, dihedrals, trihedrals, flash, multiple poles, etc.) to develop a physical description of the vessel suitable for inclusion in the classification database. The complex-valued radar returns should map directly into a description of surface feature such as edges, corners and gaps. The objective is to accomplish this task in near real-time using machine learning approaches capable of being hosted on legacy maritime radar systems (APY-10, APS-153, ZPY-4 or ZPY-3) which may have limited computing resources.

Prospective contractor(s) may need access to secure information in Phase II. The prospective contractor(s) must be U.S. owned and operated with no foreign influence as defined by DoD 5220.22-M, National Industrial Security Program Operating Manual, unless acceptable mitigating procedures can and have been implemented and approved by the Defense Security Service (DSS). The selected contractor and subcontractors must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this project as set forth by DSS and NAVAIR in order to gain access to classified information pertaining to the national defense of the United States and its allies; this will be an inherent requirement. The selected company will be required to safeguard classified material IAW DoD 5220.22-M during the advanced phases of this contract.

PHASE I: Contactors will develop concepts to leverage scattering physics to improve target detection and classification performance. Firms will demonstrate the feasibility of the concepts for technology development, target detection and classification improvement, and insertion in existing legacy APY-10, APS-153, ZPY-4 or ZPY-3 radar systems. The company should identify technical risks of their concept. The Phase I Option, if awarded, will include the initial design layout and a capabilities description to build into Phase II.

PHASE II: Using sponsor provided radar data collections, demonstrate the ability to generate vessel classification attributes suitable for inclusion in existing database structures. It is expected that the approach will provide classification attributes within 5% of actual value for 90% of combatant or non-combatant vessels with length overall greater or equal to 60m vessels which are completely illuminated, provide sufficient Doppler Resolution (5 pixels for a mast), SCR> 20dB and heading information accurate to 2 degrees. Based on the results of Phase I efforts and the Phase II Statement of Work (SOW), the company shall develop a prototype system to address the technical risks of their concepts. The company shall develop draft specifications for the different elements of the concept. The contractor shall provide details, including costs, on any modifications that might be needed for legacy radar systems to insert improved target detection and classification techniques into those radar systems. Conduct limited modification and tests in multiple maritime environments provided by the Navy to demonstrate performance with respect to intended use.

PHASE III DUAL USE APPLICATIONS: The company shall support the Navy in transitioning the technology to Navy use. The company shall develop specifications and first articles for concept unique elements and specifications for other concept elements which must have specific functionality to implement the end product. The firm will support the Navy in integrating the classification attribute generation approach [into selected legacy system in collaboration with the sponsoring agency. Coastal surveillance and air traffic control radar systems could leverage this technology for improved performance in the presence of non-cooperative contacts such as in port security systems.

REFERENCES:

1. Hwang, J-K, Lin, K-Y, Chiu, Y-L, & Deng J-H, 2006, Automatic Target Recognition Based on High-Resolution Range Profiles with Unknown Circular Range Shift, Signal Processing and Information Technology, 2006 IEEE international Symposium, 283-288.

2. Bae, J., & Goodman, N.A.,2011, Automatic Target Recognition with Unknown Orientation and Adaptive Waveforms, Radar Conference (RADAR) 2011 IEEE, 1000-1005.

KEYWORDS: Maritime Surveillance; Signature matched; aspect matched; target classification; diverse waveform transmission; machine learning

TPOC-1: 301-342-2637

TPOC-2: 301-342-9094

Questions may also be submitted through DoD SBIR/STTR SITIS website.

** TOPIC AUTHOR (TPOC) **

DoD Notice:   Between December 11, 2015 and January 10, 2016 you may talk directly with the Topic Authors (TPOC) 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 January 11, 2016 , 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 (16.1 Q&A) during the solicitation period for questions and answers, and other significant information, relevant to the SBIR 16.1 topic under which they are proposing.

If you have general questions about DoD SBIR program, please contact the DoD SBIR Help Desk at 800-348-0787 or sbirhelp@bytecubed.com