|
Multi-Sensor Automated Ship and Small Craft Classification Tools
Navy SBIR 2009.2 - Topic N092-103 NAVAIR - Mrs. Janet McGovern - [email protected] Opens: May 18, 2009 - Closes: June 17, 2009 N092-103 TITLE: Multi-Sensor Automated Ship and Small Craft Classification Tools TECHNOLOGY AREAS: Ground/Sea Vehicles, Sensors, Electronics, Battlespace ACQUISITION PROGRAM: Maritime Patrol and Reconnaissance; Multi-Mission Tactical Unmanned Air; 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: The goal of this project is to explore innovative techniques that will provide a robust multi-sensor classification tool to assist sensor operators in rapidly and accurately classifying ships and small boats in the littoral. DESCRIPTION: The current state of the art in assisted target recognition separately processes individual image frames from each sensor and forms a decision based on the weighed sum of classification confidence from each of the different imaging modalities. It is the goal of this effort to simultaneously process both Inverse Synthetic-Aperture Radar (ISAR) and Electro Optical/Infrared (EO/IR) in real time to refine tracking of individual scatters on the target which in turn may allow further refinement of the motion model and result in improved target dimension estimation and visual representation. ISAR processing algorithms track multiple point scatters over time for the purpose of focusing the final image. Many of these algorithms use the migration of individual scatters over time as inputs to the motion model whose results are then used in the focusing process. The primary goal of the ISAR motion model is to estimate the acceleration field parameterized by Doppler frequency, range, and time. The resulting motion model is generated by a best fit of the acceleration of the set of point target scatterers to the physically realizable rigid body motion of the craft. It is obvious that any number of events may ruin this fit and acceleration calculation. Clutter or sidelobe false targets may contaminate our list of target features, the target features present may result in a singular solution, or there simply may be too few detected target features. The focus of the final image frame may be compromised if based only on the set of target scattering points detected during the integration time. In many instances simultaneous ISAR and EO/IR imaging of the same vessel is possible. The desire is to investigate the possible improvements in the quality of the ISAR motion model when information from the tracking of individual structures in azimuth and elevation obtained from the EO/IR sensor is merged with the range and Doppler information on individual scatters. This may assist the accuracy and stability of the coefficients across trouble spots and smooth the fluctuation of coefficients from image frame to frame. Note: 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 be implemented and approved by the Defense Security Service (DSS). The selected contractor and/or subcontractor must be able to acquire and maintain a secret level facility and Personnel Security Clearances, in order to perform on advanced phases of this contract 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 advance phases of this contract. PHASE I: Perform a detailed analysis assessing the value of merging information from the tracking of individual structures in azimuth and elevation obtained from the EO/IR sensor with the range and Doppler information on individual scatters from the radar to improve the quality of the ISAR motion model. Develop a test plan that addresses performance metrics for use during Phase II testing. PHASE II: Design and demonstrate that the proposed algorithmic approach can improve ISAR motion model accuracy in the presence of imperfect data. The demonstration and refinement shall be undertaken using either available or DoD provided data sets. PHASE III: Work with radar system manufacturers to transition the technology to the Fleet. PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: The general methods developed could be applicable to a wide range of feature classification needs ranging from those of homeland security to the medical field. REFERENCES: 2. Paul J. Withagen, Klamer Schutte, Albert Vossepoel, and Marcel Breuers, "Automatic classification of ships from infrared (FLIR) images", Signal Processing, Sensor Fusion, and Target Recognition VIII, SPIE Proceedings Vol. 3270, Orlando, USA, 1999, pp. 180-187. KEYWORDS: Inverse Synthetic Aperture Radar; Automatic Target Recognition; Ship and Small Craft Classification; Electro-Optic Sensor; Multi-Sensor; Littoral
|