OBJECTIVE: Develop innovative concepts for an algorithm to detect airborne contacts within a suite of panoramic image data. The algorithm would alert the operator to the possible contact for more detailed investigation. DESCRIPTION: The Navy is developing a new panoramic imaging submarine mast. Currently, the Navy does not use an automated algorithm for aircraft search, but has operators manually scanning the horizon by rotating a non-panoramic mast. The Navy desires an innovative automated algorithm to detect aircraft within the video imagery with a very low false alarm rate in real time. (See References 1,2 & 3.) Some existing state of the art security systems that employ advanced algorithms in pattern matching, contrast detection, and motion detection may be applicable. Given that the data load is 20 times greater than production systems today, the algorithm should be highly parallelized such that it could be integrated into a parallelized image processing stream running on parallel processors as a portion of the processing code that builds the panoramic image. A panoramic imager in this mast will collect data over a wide range of vertical elevation and 360 degrees of azimuth. The amount of data collected will be in excess of 100 megapixels per frame, and 30 frames per second for visible data, and 25 megapixels per second for infrared data. The algorithm must be able to detect and cue for an operator moving aircraft using the smallest number of pixels and frames possible. Aircraft include small propeller patrol aircraft, fighter aircraft, and helicopters. Aircraft could be fast or stationary, seen against a background of sky or cloud, and search could occur during day or night. The Phase I effort will not require access to classified information. If need be, data of the same level of complexity as secured data will be provided to support Phase I work. The Phase II effort will likely require secure access, and the contractor will need to be prepared for personnel and facility certification for secure access. PHASE I: The company will develop concepts for the algorithm described above. The company will demonstrate the feasibility of the concepts in meeting Navy needs and will establish that the concepts can be feasibly developed into a useful product for the Navy. Feasibility will be established by material testing and analytical modeling. The small business will provide a Phase II development plan with performance goals and key technical milestones, and that will address technical risk reduction. PHASE II: Based on the results of Phase I and the Phase II development plan, the company will implement a prototype for evaluation against synthetic data, which the Navy will assist in providing. The prototype will be evaluated to determine its capability in meeting the performance goals defined in Phase II development plan and the Navy requirements for aircraft detection. System performance will be demonstrated through prototype evaluation and modeling or analytical methods over the required range of parameters including numerous deployment cycles. Evaluation results will be used to refine the prototype into an initial design that will meet Navy requirements. The company will prepare a Phase III development plan to transition the technology to Navy use. PHASE III: If Phase II is successful, the company will be expected to support the Navy in transitioning the technology for Navy use. The company will develop an algorithm for evaluation to determine its effectiveness in an operationally relevant environment. The company will support the Navy for test and validation to certify and qualify the system for Navy use. PRIVATE SECTOR COMMERCIAL POTENTIAL/DUAL-USE APPLICATIONS: Dual use applications of these algorithms would include security systems, many of which are starting to use panoramic imagers. REFERENCES: 1. Dey, Debadeepta; Geyer, Christopher; Singh, Sanjiv; Digioia, Matt ."Field and Service Robotics", July 2009.
. 2. McCandless, JW."Detection Of Aircraft In Video Sequences Using A Predictive Optical Flow Algorithm", Optical Engineering, 1999, 3: 523-530. . 3. Hauser, Gregory;Manic, Milos,"Neural Network Real Time Video Processor for Early Aircraft Detection", University of Idaho, 2009. .