You are here

Three Dimensional Ship Modeling for Submarine Combat Systems


OBJECTIVE: The objective is to develop a"two dimensional digital image to three dimensional model"conversion tool of ship digital images that enhance submarine combat system applications. DESCRIPTION: Three dimension (3D) ship models are used to support mensuration, classification, and identification tasks in a submarine combat system. 3D computer aided design (CAD) models are not widely available for most classes of ships. They must be manually developed using a variety of photographs and information from ship references such as"Jane"s Fighting Ships."Development of 3D models requires significant non recurring engineering costs upwards of $5K per model and requires skilled engineers. With several thousand classes of ships in existence today and new classes of ships being developed every year, non-recurring engineering costs are high. The capability to generate a 3D model in minutes will result in significant cost savings. Often submarines encounter vessels for which they have no 3D model. The capability to quickly build a 3D model from existing two dimension (2D) digital images in the submarine"s combat system is needed. Software is commercially available today for building 3D models from photographs. This software is based on the science of digital photogrammetry (Ref. 1, 2). This software can be broken into two categories: semi-automatic and manual methods. The semi-automatic methods do not generally work on typical 2D images of ships. These methods require near perfect digital images taken in good uniform illumination with significant overlap between images. This is usually not the case for a compilation of images taken by submarines. The manual methods require painstaking matching of points between images. These methods are much too time-consuming and complex for a typical submarine combat system operator. A method is sought that works with minimal operator intervention (Ref. 3). Model-based automated classification software uses 3D models to match images of vessels to their corresponding models. Without a 3D model for a target, the target will be mis-classified or designated as an unknown target. The capability for semi-automatically generating 3D models from 2D digital images should eventually result in a much larger model set, which will result in improved submarine combat system operator effectiveness. The Navy seeks a semi-automated method for generation of 3D models from 2D digital images requiring minimal operator intervention or editing using photogrammetric techniques. This method should use sets of images taken from a variety of ranges, cameras, sea states, weather conditions, and illumination conditions. Sophisticated image processing techniques should be used to segment vessels from land, clouds, waves, and other objects in the background. This method should be able to utilize known range information on the ship from other ownship sensors and be able to input data from known ship references, such as"Jane"s Fighting Ships". 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 a 3D model generation algorithm that meet the requirements 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 testing the algorithm on compilations of ship photographs for several ships. Specific theory/algorithms should be identified to address all steps in the 3D model generation process. 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 small business will develop a prototype 3D model generation algorithm that operates in real time on a variety of stand-alone hardware with minimal latency and operator intervention, ready for a land-based evaluation. System performance will be demonstrated through evaluation of the algorithm using a variety of sets of photographs of several classes of ships from submarine periscope data sets. 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 integrate the 3D model generation algorithm into a submarine combat system 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: As already discussed there is a market for this type of technology. Software developed under this program should be applicable with some modification to many other commercial and military applications including the modeling of aircraft, automobiles, buildings, and private vessels. REFERENCES: 1. Egels, Yves and Kasser, Michel. Digital Photogrammetry, New York: Taylor & Francis, 2002. 2. Pollefeys, Marc and Van Gool, Luc."From Images to 3D Models."Communications of the ACM, Vol. 45, Issue 7, July 2002, pp. 50-55. 3. Franken, et al."Minimizing user intervention in registering 2D images to 3D models."Visual Computing, Vol. 21, 2005, pp. 619-628.
US Flag An Official Website of the United States Government