Virtual Environments for Distributed Command and Control

DoD collects large amounts of digital imagery from diverse sources such as hospital radiologydepartments, satellites, unmanned surveillance vehicles. To systematically analyze these data,one must be able to denoise, segment, annotate, store, transmit, index, screen, and retrieveimages in a consistent and easy-to-use environment. All these tasks rely on image processingtechniques to extract information from raw imagery.Traditional image enhancement and segmentation techniques take a global view of image,processing the entire image without considering local variations. Multiscale image processingtechniques based on curvature-driven flows overcome many of the problems of traditionalprocessing methods since mutliscale techniques focus on features of data that are found atdifferent scales and resolutions.We propose to develop image enhancement and segmentation, algorithms using curvature-based flow-driven nonlinear partial differential equation imaging models and algorithms,including total variation, level-set, active contour techniques. We propose to integrate thesetechniques into Java GUI that interfaces with a database and scripting language to provideman-in-the-loop processing, feature extraction, and analysis of image data. We willdemonstrate the system on applications in medical and tactical imaging, or to Army sponsor-directed imaging applications. This technology will improve the ability to analyze, index, andsearch digital imagery.