BAYESIAN INFERENCE-BASED FUSION OF RADAR IMAGERY, MILITARY FORCES ANDTACTICAL TERRAIN MODELS IN THE IMAGE EXPLOITATION SYSTEM BALANCED TECHNOLOGY INITIATIVE

The Imagery Exploitation System/Balanced Technology Initiative (IES/BT I) inputs synthetic aperture radar (SAR) imagery and outputs probabili stically ranked interpretations of the presence and location of milita ry force membership, organization, and expected ground formations. The re are also probabilistic models of underlying terrain types from a ta ctical perspective that provide evidence supporting or denying the pre sence of forces at a location. The system compares sets of detected mi litary vehicles extracted from imagery against the models of military units and their formations to create evidence of force type and locati on. Based on this evidence, the system dynamically forms hypotheses of the presence, location and formations of military forces on the groun d, which it represents in a dynamically modified Bayesian network. The IES/BTI functional design is based on a decision theoretic model in w hich processing choices are determined as a utility function of the cu rrent state of interpretation of imagery and a top-level goal to explo it imagery as accurately and rapidly as possible, given the available data, current state of the interpretation of force hypotheses and the system processing suite.