Hyperspectral Identification for Collaborative Tracking

This proposed SBIR program will capitalize on advances in hyperspectral processing and feature-aided tracking to enhance the military’s ability to detect and track moving targets over long time periods using data from ground-based, airborne or UAV-based spectral imaging sensors. Existing multi-target tracking approaches that rely solely on spatial and temporal information from conventional electro-optical sensors fall short of demanding needs for persistent surveillance in complex environments, particularly urban areas. Recent sensor developments are removing previous limitations on near-simultaneous acquisition and utilization of high-resolution spatial, spectral and temporal information from stationary or moving platforms. Space Computer Corporation proposes to develop and demonstrate hyperspectral signature-aided methods to enhance long-term target tracking performance, with special emphasis on spectral-temporal signature extraction, signature evolution and matching to enable continuous recognition of specific targets moving in a complex scene. In this Phase II program we will refine and extend the algorithms and processing architecture, characterize performance in more realistic scenarios, and deliver software tools to demonstrate the new tracking techniques using data from existing spectral imaging sensors.