This document describes a challenge problem whose scope is two-fold. The first aspect is to develop SAR CCD algorithms that are applicable for X-band SAR imagery collected in an urban environment. The second aspect relates to effective data compression of these complex SAR images, where quality SAR CCD is the metric of performance.A set of X-band SAR imagery is being provided to support this development. To focus research onto specific areas of interest to AFRL, a number of challenge problems are defined.The data provided is complex SAR imagery from an AFRL airborne X-band SAR sensor. Some key features of this data set are: 10 repeat passes, single phase center, and single polarization (HH). In the scene observed, there are multiple buildings, vehicles, and trees. Note that the imagery has been coherently aligned to a single reference.

An innovative data mining algorithm was developed by TSC for application to longterm, wide area Ground Moving Target Indication (GMTI) radar databases obtained from both airborne and space-based Intelligence, Reconnaissance and Surveillance (ISR) systems. The algorithm can discover high-value targets of opportunity including convoys in dense civilian background traffic, and was recently demonstrated for a GMTI database collected by an operational Air Force ISR platform. Further investigations are using a realistic computer simulation of vehicle traffic. In the algorithm, vehicle detection sequences are linked over multiple scans and then analyzed by Hough Transform (HT) processing.The HT can resolve closely spaced vehicles and characterize target kinematics to provide real-time operator cueing or support GMTI radar forensic analysis. These data mining algorithms have been successfully applied to actual and simulated GMTI radar databases with a per scan probability of target detection as low as 50%, false alarm rates as high as one per km of road, and civilian vehicle densities up to 10 per km. Thus they can complement conventional tracking algorithms in areas of dense background traffic where false tracks and datato-track misassociation is a serious problem.