Visualization Techniques for Multi- and Hyperspectral Imagery Exploitation Navy SBIR FY2005.1 Sol No.: Navy SBIR FY2005.1 Topic No.: N05-018 Topic Title: Visualization Techniques for Multi- and Hyperspectral Imagery Exploitation Proposal No.: N051-018-1590 Firm: Technical research Associates, Inc. P.O. Box 9499 San Diego, California 92169 Contact: Edwin Winter Phone: (858) 539-0912 Web Site: www.tracam.com Abstract: Hyperspectral and multi-spectral sensors are assuming a greater role in all aspects of military surveillance and intelligence. While many excellent packages exist for analyzing this data, there has been minimal progress made towards the development of techniques that focus on supporting/aiding the hyperspectral imagery analyst in procedures for semi-automatic extraction of targets. Imagery analyst often rely on scene context to aid in identification of targets, and the identification of scene elements such as road surface, vegetation, building materials, etc. is not a part of target detection software. There is a major divide between scene classification techniques that are developed for terrain classification and target detection algorithms that are often developed for real-time sensors. We propose to develop a software environment that will provide both advanced target detection capability as well as the ability to use scene classification to determine the context of the target. Benefits: The proposed approach has potential application to both the federal Government and to commercial interests. The proposed results of this SBIR will have potential use by the Federal Government in the both the Terrain Classification and Military Target Detection areas. Hyperspectral sensors are being used now for terrain classification. By examining the spectrum of a point on the ground the material can be identified. The implications of hyperspectral sensors for military intelligence applications include the detection of hidden targets, mine detection, the identification of vehicles in a convoy, changes in a military deployment that may signify attack status, and the assessment of new weapons. Civilian and commercial hyperspectral systems are also being applied to a variety of applications from geology and agriculture to search and rescue. The proposed software will aid the interpretation of that imagery by more optimally combining the classification and detection functions. Return