Multi-sensor Registration Tools

The objective of this effort is to develop innovative autonomous geo-registration technologies in the form of a software toolkit for the spatial alignment of image, signal intelligence (SIGINT), and ground moving target indicator (GMTI) data collected fromthe battlespace. Some work has been directed toward the spatial alignment of images, SIGINT and GMTI data collected from the battlespace. Yet, the understanding of precisely how to extract and use this data for relative and absolute registration islimited. The focus of this research is on the design of a generic concept of a geo-reference invariant feature that can be extracted from each data source and the development of generic algorithms for correlating salient features across the multiple datasources and a fiducial database for relative and absolute registration. Example features that cross multiple source data domains are radio/TV transmission towers, command and control centers, road intersections, fixed search radar towers, and cellularphone towers. Trade-off studies will identify strategies for a reliable, flexible system that can tie disparate types of sensor data together, provide tractable error/uncertainty handling, and identify measures of effectiveness for automatic convergence tominimize human intervention. An equally important focus is the implementation of these algorithms as a software toolkit to enable the integration of different registration algorithms for multi-source data. The proposed SMART toolkit concept is will employan expert system based approach to automatically select the appropriate geo-registration and correlation algorithm(s) for a multi-source data domains. Accurate and automated geo-registration is of interest to the Air Force. Military applications mayinvolve platform or ground station geo-registration services support. These geo-registration services would enhance performance for various processes like targeting, tracking, fusion, and change detection. Autonomous data registration algorithms are neededin the growing area of Geospatial Information Systems (GIS) and geographic image analysis tools. The product resulting from this effort can be integrated as a plug-in to commercial applications such as ESRI's ArcView, ERDAS' IMAGINE, and K-RSI's ENVI toenable the automatic alignment of different data sources.