Sensor management based on cross-entropy in interacting multiple model Kalman filter

Multisensor systems have been widely used in a variety of civilian and military applications. While sensor management is one of the most important parts of multisensor system. Many techniques of sensor management have been proposed and applied. This paper describes a method using a cross-entropy-based sensor effectiveness metric for sensor assignment in interacting multiple model Kalman filter (IMMKF). The expected cross-entropy is computed for the sensor target pairing on each scan. Then the constrained globally optimum assignment of sensors to targets is calculated and applied.