Construction of Dense 3D Ship Models from Submarine Image Collections Navy SBIR FY2013.1 Sol No.: Navy SBIR FY2013.1 Topic No.: N131-024 Topic Title: Construction of Dense 3D Ship Models from Submarine Image Collections Proposal No.: N131-024-0869 Firm: Toyon Research Corp. 6800 Cortona Drive Goleta, California 93117-3021 Contact: Michael Moore Phone: (805) 968-6787 Web Site: www.toyon.com Abstract: To create robust automated video analysis techniques for extracting, measuring, classifying, and identifying objects-of-interest, 3D object models have many benefits. Manual creation of a full range of 3D models would be a daunting task. A method for automatically generating 3D models from data gathered at sea would make populating a 3D model database practical as well as enabling updates to be generated as more information is gathered. Toyon Research Corporation proposes to implement a method for constructing a 3D model from a series of submarine-acquired 2D images. Toyon has developed industry-leading techniques for dense 3D reconstruction from moving sensor platforms. The effort will include development of methods for segmenting target ship data from marine backgrounds, automatically estimating the relationship among image viewpoints, compensating for target ship motion, and integrating results into a 3D model. A performance metric suitable for predicting automated target recognition performance will be created. The initial software implementation of the proposed algorithm will be used to assess the potential of the proposed reconstruction process and provide the basis for a recommended system design. Benefits: Successful completion of the proposed research and development effort will produce a real-time, video-based, passive, automated 3D modeling system. The primary purpose of the technology will be to enable low-cost generation of 3D models to support automated target recognition. The developed technology is thus expected to be directly applicable to automated target recognition systems deployed by the Army, Navy, Air Force, and SOCOM. The main benefits are expected in military applications. However, an accurate and easy-to-use 3D model generation solution could have many desirable benefits in the commercial market. For example, 3D models would help improve the performance of commercial automated recognition systems, such as those in automotive and marine collision avoidance systems or as part of the video analytics package in unattended security systems. This would provide significant advantages to commercial surveillance applications ranging in scale from harbor, warehouse, or facility protection down to home or store site monitoring. Return